mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
* chore: update cutlass to v3.8.0 Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * refactor: update include directives for consistency and organization in weightOnlyBatchedGemv headers Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * Fix fpA_intB_gemm compilation Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> --------- Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| common.h | ||
| converter.h | ||
| cudaCoreGemm.cu | ||
| cudaCoreGemm.h | ||
| 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 | ||