kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-04 02:02:01 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
baa250d1d6
TensorRT-LLMs/cpp/tensorrt_llm/common
History
Perkz Zheng 71ccc07d2b
[None][feat] update trtllm-gen to support groupsTokensHeadsQ (#10261) 
Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Co-authored-by: Bo Li <22713281+bobboli@users.noreply.github.com>
2026-01-15 02:24:25 -05:00
..
assert.cpp [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
attentionOp.cpp [None][feat] update trtllm-gen to support groupsTokensHeadsQ (#10261) 2026-01-15 02:24:25 -05:00
attentionOp.h [TRTLLM-9805][feat] Skip Softmax Attention. (#9821) 2025-12-21 02:52:42 -05:00
CMakeLists.txt [https://nvbugs/5451205][feat] Add cuBLASLt NVFP4 GEMM backend support (#7943) 2025-10-23 15:55:10 +08:00
cublasMMWrapper.cpp [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
cublasMMWrapper.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
cublasVersionCheck.h Initial commit 2023-09-20 00:29:41 -07:00
cudaBf16Fallbacks.cuh [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
cudaBufferUtils.cuh [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
cudaDriverWrapper.cpp [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
cudaDriverWrapper.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
cudaFp8Utils.cu [TRTLLM-9578][feat] make PDL enabled by default (#9695) 2025-12-25 07:15:24 -05:00
cudaProfilerUtils.cpp [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
cudaTypeUtils.cuh [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
customAllReduceUtils.h [TRTLLM-8821][feat] Apply AutoTuner to AllReduce Op for strategy tuning. (#8531) 2026-01-05 15:44:37 +08:00
envUtils.cpp [TRTLLM-9578][feat] make PDL enabled by default (#9695) 2025-12-25 07:15:24 -05:00
envUtils.h [TRTLLM-9805][feat] Skip Softmax Attention. (#9821) 2025-12-21 02:52:42 -05:00
ipUtils.cpp [None][feat] Support Mooncake transfer engine as a cache transceiver backend (#8309) 2025-12-19 10:09:51 +08:00
ipUtils.h [None][feat] Support Mooncake transfer engine as a cache transceiver backend (#8309) 2025-12-19 10:09:51 +08:00
jsonSerializeOptional.h Update TensorRT-LLM (#2436) 2024-11-12 15:27:49 +08:00
lamportUtils.cuh [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
logger.cpp [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
mathUtils.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
mcastDevMemUtils.cpp [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
mcastDevMemUtils.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
memoryUtils.cu [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
memoryUtils.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
ncclUtils.cpp [None][fix] [fix] Make NCCL resource manager destructor exception-safe (#10166) 2026-01-03 10:25:05 -05:00
ncclUtils.h [None][fix] [fix] Make NCCL resource manager destructor exception-safe (#10166) 2026-01-03 10:25:05 -05:00
nvtxUtils.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
opUtils.cpp [None][fix] [fix] Make NCCL resource manager destructor exception-safe (#10166) 2026-01-03 10:25:05 -05:00
opUtils.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
quantTypeUtils.cuh [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
reduceKernelUtils.cuh [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
safetensors.cpp [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
safetensors.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
stlUtils.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
stringUtils.cpp [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
timestampUtils.cpp [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
timestampUtils.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
tllmException.cpp [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00
vec_dtypes.cuh [TRTLLM-7318][feat] MnnvlThroughput AlltoAll implementation. (#7499) 2025-10-27 13:23:06 -04:00
workspace.h [None][fix] Introduce inline namespace to avoid symbol collision (#9541) 2025-12-12 23:32:15 +08:00