mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-22 19:52:38 +08:00
* Update TensorRT-LLM --------- Co-authored-by: Timur Abishev <abishev.timur@gmail.com> Co-authored-by: MahmoudAshraf97 <hassouna97.ma@gmail.com> Co-authored-by: Saeyoon Oh <saeyoon.oh@furiosa.ai> Co-authored-by: hattizai <hattizai@gmail.com> |
||
|---|---|---|
| .. | ||
| common.h | ||
| converter.h | ||
| cudaCoreGemm.cu | ||
| cudaCoreGemm.h | ||
| details.h | ||
| int8SQ.cu | ||
| int8SQ.h | ||
| kernel.h | ||
| kernelDispatcher.h | ||
| kernelDispatcherBf16Int4GroupwiseColumnMajorFalse.cu | ||
| kernelDispatcherBf16Int4GroupwiseColumnMajorInterleavedTrue.cu | ||
| kernelDispatcherBf16Int4PerChannelColumnMajorFalse.cu | ||
| kernelDispatcherBf16Int4PerChannelColumnMajorInterleavedTrue.cu | ||
| kernelDispatcherBf16Int8PerChannelColumnMajorFalse.cu | ||
| kernelDispatcherBf16Int8PerChannelColumnMajorInterleavedTrue.cu | ||
| kernelDispatcherFp16Int4GroupwiseColumnMajorFalse.cu | ||
| kernelDispatcherFp16Int4GroupwiseColumnMajorInterleavedTrue.cu | ||
| kernelDispatcherFp16Int4PerChannelColumnMajorFalse.cu | ||
| kernelDispatcherFp16Int4PerChannelColumnMajorInterleavedTrue.cu | ||
| kernelDispatcherFp16Int4PerChannelColumnMajorTrue.cu | ||
| kernelDispatcherFp16Int8PerChannelColumnMajorFalse.cu | ||
| kernelDispatcherFp16Int8PerChannelColumnMajorInterleavedTrue.cu | ||
| kernelDispatcherFp16Int8PerChannelColumnMajorTrue.cu | ||
| kernelLauncher.h | ||
| utility.h | ||