[Doc] Add vLLM Beijing meetup slide (#14938)

Chen Zhang committed over 1 year ago

[Misc][XPU] Use None as device capacity for XPU (#14932)

Yan Ma committed over 1 year ago

[V1] Remove input cache client (#14864)

Cyrus Leung committed over 1 year ago

[V1] [Spec Decode] Support random sampling for spec decode (#13933)

Lily Liu committed over 1 year ago

[Benchmark] Do not save detailed info to json by default (#14879)

Simon Mo committed over 1 year ago

[Misc] Replace os environ to monkeypatch in test suite (#14516)

Sibi committed over 1 year ago

[BugFix] Fix MLA + V1 + TP==1 causing reinitialization of cuda context (#14910)

Lucas Wilkinson committed over 1 year ago

[V1][Minor] Add __repr__ to ConstantList (#14907)

Woosuk Kwon committed over 1 year ago

[V1] Optimize the overhead of rewinding (#14905)

Woosuk Kwon committed over 1 year ago

[CI/Build] Update defaults for test reproducibility (#14893)

Cyrus Leung committed over 1 year ago

[CI] Nightly Tests (#14898)

Robert Shaw committed over 1 year ago

[V1] Enable Entrypoints Tests (#14903)

Robert Shaw committed over 1 year ago

[Doc] Add guidance for using `ccache` with `pip install -e .` in doc (#14901)

Vadim Gimpelson committed over 1 year ago

[Misc] Catching Ray Compiled Graph PP test failures for V1 (#14847)

Rui Qiao committed over 1 year ago

[V1][BugFix] Detect interleaved sliding window attention (#14896)

Woosuk Kwon committed over 1 year ago

[BugFix][V1] Fix overhead related to bad_words sampling when not in use (#14894)

Nick Hill committed over 1 year ago

Revert "[Bugfix] Limit profiling run sequence length by max_model_len (#14785) (#14892)

Cyrus Leung committed over 1 year ago

[Bugfix] Explicitly disable Phi-4-multimodal in V1 (#14889)

Cyrus Leung committed over 1 year ago

[Bugfix] Limit profiling run sequence length by max_model_len (#14785)

Kyle Sayers committed over 1 year ago

[V1] [Spec Decode] Fix ngram tests (#14878)

Lily Liu committed over 1 year ago