TensorRT-LLMs/cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin
Perkz Zheng 0722717ec0
[None][fix] trtllm-gen regression in PR 8301 (#8426)
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
2025-10-17 03:21:31 -07:00
..
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCustomP32MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCustomP32MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCustomP32VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCustomP32VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCustomP64MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCustomP64MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCustomP64VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvCustomP64VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCustomP32MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCustomP32MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCustomP32VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCustomP32VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCustomP64MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCustomP64MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCustomP64VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvCustomP64VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128SeparateQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128SeparateQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128SeparateQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk192HV128SeparateQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvGmemSepVarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ64Kv128Persistent2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvGmemSepVarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ64Kv128Persistent2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvBfloat16OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCustomP32MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCustomP32MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCustomP32VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCustomP32VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCustomP64MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCustomP64MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCustomP64VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvCustomP64VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCustomP32MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCustomP32MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCustomP32VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCustomP32VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCustomP64MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCustomP64MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCustomP64VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvCustomP64VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128SeparateQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128SeparateQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128SeparateQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk192HV128SeparateQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP32VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta128PagedKvDenseP64VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvGmemSepVarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ64Kv128Persistent2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP32VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvGmemSepVarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ64Kv128Persistent2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ64Kv128Static2CtaKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta256PagedKvDenseP64VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP32VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvCgaVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvGmemSepVarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvVarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvVarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ8Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ8Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ16Kv64PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ16Kv64StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ64Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OBfloat16HQk576HV512HVPerCta512PagedKvDenseP64VarSeqQ64Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE2m1H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCustomP32MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCustomP32MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCustomP32VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCustomP32VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCustomP64MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCustomP64MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCustomP64VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvCustomP64VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCustomP32MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCustomP32MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCustomP32VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCustomP32VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCustomP64MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCustomP64MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCustomP64VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvCustomP64VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OE4m3H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCustomP32MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCustomP32MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCustomP32VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCustomP32VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCustomP64MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCustomP64MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCustomP64VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvCustomP64VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCustomP32MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCustomP32MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCustomP32VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCustomP32VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCustomP64MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCustomP64MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCustomP64VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvCustomP64VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvE4m3OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCustomP32MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCustomP32MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCustomP32VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCustomP32VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCustomP64MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCustomP64MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCustomP64VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvCustomP64VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCustomP32MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCustomP32MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCustomP32VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCustomP32VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCustomP64MultiCtasKvCgaVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCustomP64MultiCtasKvVarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCustomP64VarSeqQ128Kv128PersistentKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvCustomP64VarSeqQ128Kv128StaticKeepsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PackedQkvCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PackedQkvCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PackedQkvDenseVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PackedQkvDenseVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PackedQkvSlidingOrChunkedCausalVarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm100fKernel_QkvFp16OFp16H256PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H64HVPerCta64PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvDenseP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP32MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP32MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP32VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP32VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP32VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP64MultiCtasKvCgaVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP64MultiCtasKvVarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP64VarSeqQ8Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128PersistentSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP64VarSeqQ16Kv128StaticSwapsAbForGen_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128PersistentContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
FmhaSm103aKernel_QE4m3KvE2m1OE4m3H128HVPerCta128PagedKvSlidingOrChunkedCausalP64VarSeqQ128Kv128StaticContext_cubin.cpp [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00
kernelMetaInfo.h [None][fix] trtllm-gen regression in PR 8301 (#8426) 2025-10-17 03:21:31 -07:00