| .. |
|
common.h
|
Update TensorRT-LLM (#2333)
|
2024-10-15 15:28:40 +08:00 |
|
converter.h
|
feat: Update cutlass (#2981)
|
2025-03-26 22:36:27 +08:00 |
|
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
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
int8SQ.cu
|
Update TensorRT-LLM (#1763)
|
2024-06-11 16:59:02 +08:00 |
|
int8SQ.h
|
Update TensorRT-LLM (#1358)
|
2024-03-26 20:47:14 +08:00 |
|
kernel.h
|
[feat] Optimizations on weight-only batched gemv kernel (#5420)
|
2025-06-30 10:20:16 +08:00 |
|
kernelDispatcher.h
|
feat: Update cutlass (#2981)
|
2025-03-26 22:36:27 +08:00 |
|
kernelDispatcherBf16Int4GroupwiseColumnMajorInterleavedForHopperTrue.cu
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
kernelDispatcherBf16Int4GroupwiseColumnMajorInterleavedTrue.cu
|
Update TensorRT-LLM (#2502)
|
2024-11-26 16:51:34 +08:00 |
|
kernelDispatcherBf16Int4PerChannelColumnMajorInterleavedForHopperTrue.cu
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
kernelDispatcherBf16Int4PerChannelColumnMajorInterleavedTrue.cu
|
Update TensorRT-LLM (#1492)
|
2024-04-24 14:44:22 +08:00 |
|
kernelDispatcherBf16Int8GroupwiseColumnMajoInterleavedForHopperTrue.cu
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
kernelDispatcherBf16Int8GroupwiseColumnMajorInterleavedTrue.cu
|
Update TensorRT-LLM (#2333)
|
2024-10-15 15:28:40 +08:00 |
|
kernelDispatcherBf16Int8PerChannelColumnMajorInterleavedForHopperTrue.cu
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
kernelDispatcherBf16Int8PerChannelColumnMajorInterleavedTrue.cu
|
Update TensorRT-LLM (#1492)
|
2024-04-24 14:44:22 +08:00 |
|
kernelDispatcherFp16Int4GroupwiseColumnMajorInterleavedForHopperTrue.cu
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
kernelDispatcherFp16Int4GroupwiseColumnMajorInterleavedTrue.cu
|
Update TensorRT-LLM (#1492)
|
2024-04-24 14:44:22 +08:00 |
|
kernelDispatcherFp16Int4PerChannelColumnMajorInterleavedForHopperTrue.cu
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
kernelDispatcherFp16Int4PerChannelColumnMajorInterleavedTrue.cu
|
Update TensorRT-LLM (#1492)
|
2024-04-24 14:44:22 +08:00 |
|
kernelDispatcherFp16Int8GroupwiseColumnMajorInterleavedForHopperTrue.cu
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
kernelDispatcherFp16Int8GroupwiseColumnMajorInterleavedTrue.cu
|
Update TensorRT-LLM (#2333)
|
2024-10-15 15:28:40 +08:00 |
|
kernelDispatcherFp16Int8PerChannelColumnMajorInterleavedForHopperTrue.cu
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
kernelDispatcherFp16Int8PerChannelColumnMajorInterleavedTrue.cu
|
Update TensorRT-LLM (#1492)
|
2024-04-24 14:44:22 +08:00 |
|
kernelLauncher.h
|
feat: Add FP8 support for SM 120 (#3248)
|
2025-04-14 16:05:41 -07:00 |
|
utility.h
|
[feat] Optimizations on weight-only batched gemv kernel (#5420)
|
2025-06-30 10:20:16 +08:00 |
