kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-23 04:03:22 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
c4c7dd3517
TensorRT-LLMs/cpp/tensorrt_llm/pybind/runtime
History
kanghui0204 6f3922f318
feat: Low Precision Allreduce for PCIe based GPU (#4344) 
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>
2025-05-20 06:53:46 +08:00
..
bindings.cpp feat: Low Precision Allreduce for PCIe based GPU (#4344) 2025-05-20 06:53:46 +08:00
bindings.h Update TensorRT-LLM (#2413) 2024-11-05 16:27:06 +08:00