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
..
__init__.py	chore: Fix pipeline break caused by previous PR (#4081) rebase + pipeline reuse (#4169)	2025-05-09 12:51:02 +08:00
communicator.py	chore: bump version to 0.19.0 (#3598) (#3841)	2025-04-29 16:57:22 +08:00
ops.py	feat: Low Precision Allreduce for PCIe based GPU (#3851)	2025-05-14 16:45:43 +08:00