TensorRT-LLMs/cpp/tensorrt_llm/kernels/weightOnlyBatchedGemv
Cheng Hang 15c293a90b
[None][feat] Enable nvfp4 cuda core for sm120 (#8620)
Signed-off-by: Cheng Hang <chang@nvidia.com>
2025-10-29 12:39:03 +08:00
..
common.h
converter.h
cudaCoreGemm.cu [NVBUG-5304516/5319741]Qwen2.5VL FP8 support (#5029) 2025-07-09 23:16:42 +08:00
cudaCoreGemm.h [NVBUG-5304516/5319741]Qwen2.5VL FP8 support (#5029) 2025-07-09 23:16:42 +08:00
cudaCoreGemmNVFP4.cu [None][feat] Enable nvfp4 cuda core for sm120 (#8620) 2025-10-29 12:39:03 +08:00
cudaCoreGemmNVFP4.h [None][feat] Enable nvfp4 cuda core for sm120 (#8620) 2025-10-29 12:39:03 +08:00
details.h
int8SQ.cu
int8SQ.h
kernel.h
kernelDispatcher.h
kernelDispatcherBf16Int4GroupwiseColumnMajorInterleavedForHopperTrue.cu
kernelDispatcherBf16Int4GroupwiseColumnMajorInterleavedTrue.cu
kernelDispatcherBf16Int4PerChannelColumnMajorInterleavedForHopperTrue.cu
kernelDispatcherBf16Int4PerChannelColumnMajorInterleavedTrue.cu
kernelDispatcherBf16Int8GroupwiseColumnMajoInterleavedForHopperTrue.cu
kernelDispatcherBf16Int8GroupwiseColumnMajorInterleavedTrue.cu
kernelDispatcherBf16Int8PerChannelColumnMajorInterleavedForHopperTrue.cu
kernelDispatcherBf16Int8PerChannelColumnMajorInterleavedTrue.cu
kernelDispatcherFp16Int4GroupwiseColumnMajorInterleavedForHopperTrue.cu
kernelDispatcherFp16Int4GroupwiseColumnMajorInterleavedTrue.cu
kernelDispatcherFp16Int4PerChannelColumnMajorInterleavedForHopperTrue.cu
kernelDispatcherFp16Int4PerChannelColumnMajorInterleavedTrue.cu
kernelDispatcherFp16Int8GroupwiseColumnMajorInterleavedForHopperTrue.cu
kernelDispatcherFp16Int8GroupwiseColumnMajorInterleavedTrue.cu
kernelDispatcherFp16Int8PerChannelColumnMajorInterleavedForHopperTrue.cu
kernelDispatcherFp16Int8PerChannelColumnMajorInterleavedTrue.cu
kernelLauncher.h
utility.h