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
b15f57763d
TensorRT-LLMs/cpp
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
..
cmake chore: enhance the cmake experience by ignoring the additional semicolon (#3992) 2025-05-08 18:43:36 +08:00
include/tensorrt_llm Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979) 2025-05-12 22:32:29 +02:00
kernels/xqa infra: open source XQA kernels (#3762) 2025-04-30 18:05:15 +08:00
micro_benchmarks feat: support add internal cutlass kernels as subproject (#3658) 2025-05-06 11:35:07 +08:00
tensorrt_llm feat: Low Precision Allreduce for PCIe based GPU (#3851) 2025-05-14 16:45:43 +08:00
tests Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979) 2025-05-12 22:32:29 +02:00
CMakeLists.txt Cherry-pick trtllm-gen from feat/llama4 to main (#4086) 2025-05-08 14:13:01 -07:00
conandata.yml infra: add conan (#3744) 2025-04-30 11:53:14 -07:00
conanfile.py infra: add conan (#3744) 2025-04-30 11:53:14 -07:00