GitLab

[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942)
Co-authored-by: Andrew Feldman <afeld2012@gmail.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>

Co-authored-by: hezhihui <hzh7269@modelbest.cn>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: ywang96 <ywang@roblox.com>
Co-authored-by: xwjiang2010 <87673679+xwjiang2010@users.noreply.github.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>

Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>

[ci][distributed] fix some cuda init that makes it necessary to use spawn (#5991)

Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: Robert Shaw <rshaw@neuralmagic>

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

[CI/Test] improve robustness of test by replacing del with context manager (vllm_runner) (#5357)

[CI/Test] improve robustness of test by replacing del with context manager (hf_runner) (#5347)

Co-authored-by: Roger Wang <ywang@roblox.com>

Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>

[Bug fix][Core] assert num_new_tokens == 1 fails when SamplingParams.n is not 1 and max_tokens is large & Add tests for preemption (#4451)

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