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
..
cubin	[None][fix] trtllm-gen regression in PR 8301 (#8426)	2025-10-17 03:21:31 -07:00
CMakeLists.txt	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
fmhaKernels.h	[TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086)	2025-10-14 08:23:16 -07:00
fmhaReduction.cu	[None][feat] support gpt-oss with fp8 kv cache (#7612)	2025-09-15 02:17:37 +08:00
fmhaReduction.h	[None][feat] Optimize MLA kernels with separate reduction kernels (#7597)	2025-09-09 16:58:44 +08:00
fmhaRunner.cpp	[TRTLLM-4629] [feat] trtllm-gen kernels support sm103 (#7570)	2025-09-07 10:04:10 +08:00
fmhaRunner.h	optimize cudaMemGetInfo for TllmGenFmhaRunner (#3907)	2025-04-29 14:17:07 +08:00
fmhaRunnerParams.h	[TRTLLM-8536][feat] Update trtllm gen fmha kernels to support block sparse attention (#8301)	2025-10-13 05:54:48 -07:00
kernelParams.h	[TRTLLM-8536][feat] Update trtllm gen fmha kernels to support block sparse attention (#8301)	2025-10-13 05:54:48 -07:00
kernelUtils.h	[None][feat] Optimize MLA kernels with separate reduction kernels (#7597)	2025-09-09 16:58:44 +08:00