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
476d7003f8
TensorRT-LLMs/cpp/tensorrt_llm
History
Julien Debache 0c6c8eaffd
fix: 5197419 and removed unused runtime kernels (#3631) 
- Removed kernel under test call, as it was not needed
- Removed kernel itself
- Removed kernel tests
- Removed other unused kernels and their tests
- Some static analysis clean up
2025-04-23 18:04:50 +02:00
..
batch_manager fix: 5197419 and removed unused runtime kernels (#3631) 2025-04-23 18:04:50 +02:00
common fix: Intercept the error of multi-rank binding to a single card (#3525) 2025-04-23 15:50:18 +08:00
cutlass_extensions/include/cutlass_extensions feat: Update cutlass (#2981) 2025-03-26 22:36:27 +08:00
executor bug: Fix hang bug when context server doesn't have enough capacity for KV Cache (#3095) 2025-04-21 15:16:55 +08:00
executor_worker Update TensorRT-LLM (#2792) 2025-02-18 21:27:39 +08:00
kernels Add smart router for moe (#3641) 2025-04-23 12:21:59 +08:00
layers fix: Eagle decoding (#3456) 2025-04-11 22:06:38 +08:00
plugins refactor: Clean up CMakeLists.txt (#3479) 2025-04-18 14:39:29 +08:00
pybind fix: Fix C++ decoder synchronization in PyTorch (#3106) 2025-04-23 23:55:27 +08:00
runtime fix: 5197419 and removed unused runtime kernels (#3631) 2025-04-23 18:04:50 +02:00
thop Add smart router for moe (#3641) 2025-04-23 12:21:59 +08:00
CMakeLists.txt Fix double link to fp8_blockscale_gemm_src (#3707) 2025-04-23 10:16:07 +08:00