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
ff0f37bcf8
TensorRT-LLMs/cpp/tensorrt_llm/pybind
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
..
batch_manager refactor: Copy sequence lengths once in decoder setup (#4102) 2025-05-16 22:03:55 +08:00
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 (#4344) 2025-05-20 06:53:46 +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 fix: [nvbugs/5287097] Align PP layer distribution between pytorch and TRT flow. (#4399) 2025-05-19 14:25:36 -07:00
CMakeLists.txt refactor: Move ModelSpec to core library (#3980) 2025-05-04 01:39:09 +08:00