kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
da8c7372d4
TensorRT-LLMs/cpp/tensorrt_llm/kernels/userbuffers
History
Yuan Tong 32b244af38
feat: reduce unnecessary kernel generation (#5476) 
Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
2025-07-04 14:37:49 +08:00
..
CMakeLists.txt feat: reduce unnecessary kernel generation (#5476) 2025-07-04 14:37:49 +08:00
ipcsocket.cpp Update TensorRT-LLM (#2532) 2024-12-04 21:16:56 +08:00
ipcsocket.h Update TensorRT-LLM (#2532) 2024-12-04 21:16:56 +08:00
ub_allocator.cpp feat: Introduce UB allocator for pytorch flow (#3257) 2025-04-08 18:39:49 +08:00
ub_allocator.h feat: Introduce UB allocator for pytorch flow (#3257) 2025-04-08 18:39:49 +08:00
ub_interface.cpp feat: Introduce UB allocator for pytorch flow (#3257) 2025-04-08 18:39:49 +08:00
ub_interface.h feat: Introduce UB allocator for pytorch flow (#3257) 2025-04-08 18:39:49 +08:00
userbuffers-host.cpp Update TensorRT-LLM (#2792) 2025-02-18 21:27:39 +08:00
userbuffers.cu feat: Add Mixture of Experts FP8xMXFP4 support (#4750) 2025-06-09 13:25:04 +08:00
userbuffers.h None - Add one-shot version for UB AR NORM FP16/BF16 (#2995) 2025-03-31 11:16:03 +08:00
userbuffersManager.cpp feat: Introduce UB allocator for pytorch flow (#3257) 2025-04-08 18:39:49 +08:00
userbuffersManager.h feat: Introduce UB allocator for pytorch flow (#3257) 2025-04-08 18:39:49 +08:00
utils.h Update TensorRT-LLM (#2783) 2025-02-13 18:40:22 +08:00