GitLab

 [Speculative Decoding] Support draft model on different tensor-parallel size than target model (#5414)

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)

Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Abhilash Majumder <abhilash.majumder@intel.com>
Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>

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

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

Co-authored-by: Cade Daniel <edacih@gmail.com>
Co-authored-by: Cade Daniel <cade@anyscale.com>

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

[Core][Distributed] support both cpu and device tensor in broadcast tensor dict (#4660)

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)