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
9e7b50aefb
TensorRT-LLMs/cpp/tensorrt_llm
History
Bo Deng 9e7b50aefb
[TRTLLM-9752][fix] WAR: Disable PDL for quant kernels to fix accuracy issues (#10285) 
Signed-off-by: Bo Deng <deemod@nvidia.com>
2026-01-03 14:34:55 +08:00
..
batch_manager [https://nvbugs/5625990][fix] Respect VSWA scheme when doing block store for reuse and load block for reuse in KV cache manager (#10183) 2025-12-29 14:29:14 +08:00
common [TRTLLM-9578][feat] make PDL enabled by default (#9695) 2025-12-25 07:15:24 -05:00
cutlass_extensions/include/cutlass_extensions [TRTLLM-9578][feat] make PDL enabled by default (#9695) 2025-12-25 07:15:24 -05:00
deep_ep [TRTLLM-9197][infra] Move thirdparty stuff to it's own listfile (#8986) 2025-11-20 16:44:23 -08:00
deep_gemm [TRTLLM-9211][infra] Minor fixes to 3rdparty/CMakelists (#9365) 2025-11-23 22:57:02 -08:00
executor [https://nvbugs/5702786][fix] Fix race conditions in KV cache communication during unexpected termination (#10076) 2025-12-23 14:09:51 +02:00
executor_worker Update TensorRT-LLM (#2792) 2025-02-18 21:27:39 +08:00
flash_mla [TRTLLM-9211][infra] Minor fixes to 3rdparty/CMakelists (#9365) 2025-11-23 22:57:02 -08:00
kernels [TRTLLM-9752][fix] WAR: Disable PDL for quant kernels to fix accuracy issues (#10285) 2026-01-03 14:34:55 +08:00
layers [None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127) 2025-10-27 13:12:31 -04:00
nanobind [TRTLLM-7735][feat] Attention NVFP4 out support for torch compile (#9740) 2025-12-27 00:07:20 +08:00
plugins [None][feat] Enable NCCL_SYMMETRIC as default fallback for AllReduce (#9314) 2025-12-07 09:43:26 -08:00
pybind [TRTLLM-7735][feat] Attention NVFP4 out support for torch compile (#9740) 2025-12-27 00:07:20 +08:00
runtime [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
testing fix: Improve chunking test and skip empty kernel calls (#5710) 2025-07-04 09:08:15 +02:00
thop [TRTLLM-7735][feat] Attention NVFP4 out support for torch compile (#9740) 2025-12-27 00:07:20 +08:00
CMakeLists.txt [None][feat] Support Mooncake transfer engine as a cache transceiver backend (#8309) 2025-12-19 10:09:51 +08:00