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
7c828d767f
TensorRT-LLMs/cpp/tensorrt_llm/pybind
History
kanghui0204 5e634dd1bd
feat: Low Precision Allreduce for PCIe based GPU (#3851) 
This PR adds a customized allreduce to TensorRT-LLM. The new allreduce is used for communication on PCIe-based GPUs via low-precision quantization, which can accelerate the PCIe allreduce process.

Signed-off-by: Hui Kang <hkang@nvidia.com>
Co-authored-by: Hui Kang <hkang@nvidia.com>
2025-05-14 16:45:43 +08:00
..
batch_manager [TRTLLM-5050][feat] Enable per-request stats with PyT backend (#4156) 2025-05-12 21:35:15 -04:00
common fix: Move all casters to customCasters. (#3945) 2025-05-02 19:08:28 +08:00
executor Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979) 2025-05-12 22:32:29 +02:00
runtime feat: Low Precision Allreduce for PCIe based GPU (#3851) 2025-05-14 16:45:43 +08:00
testing refactor: Move ModelSpec to core library (#3980) 2025-05-04 01:39:09 +08:00
userbuffers fix: Move all casters to customCasters. (#3945) 2025-05-02 19:08:28 +08:00
bindings.cpp refactor: Move ModelSpec to core library (#3980) 2025-05-04 01:39:09 +08:00
CMakeLists.txt refactor: Move ModelSpec to core library (#3980) 2025-05-04 01:39:09 +08:00