GitLab

[distributed][misc] keep consistent with how pytorch finds libcudart.so (#6346)

[core][distributed] add zmq fallback for broadcasting large objects (#6183)

Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>

[bugfix][distributed] do not error if two processes do not agree on p2p capability (#5612)

[Core][Distributed] add coordinator to reduce code duplication in tp and pp (#5293)

Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>

[Core][Distributed] refactor pynccl to hold multiple communicators (#4591)

Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>

Co-authored-by: Danny Guinther <dguinther@neuralmagic.com>

[Core][Distributed] use existing torch.cuda.device context manager (#4318)

[Bugfix] Fix CustomAllreduce pcie nvlink topology detection (#3974) (#4159)

[Core] Add integrity check during initialization; add test for it (#4155)

[WIP][Core][Refactor] move vllm/model_executor/parallel_utils into vllm/distributed and vllm/device_communicators (#3950)