[Bugfix] Fix glm4.1v video inference issue (#22067)

Isotr0py committed over 1 year ago

Improve documentation of `ModelConfig.try_get_generation_config` to prevent future confusion (#21526)

Harry Mellor committed over 1 year ago

Deprecate `--disable-log-requests` and replace with `--enable-log-requests` (#21739)

Harry Mellor committed over 1 year ago

[Docs] use `uv` in CPU installation docs (#22089)

David Xia committed over 1 year ago

[BugFix] Don't change title of top-level process (#22032)

Nick Hill committed over 1 year ago

[BugFix] Update AttnFusionPass cache key (#21947)

Richard Zou committed over 1 year ago

[Refactor] Fix Compile Warning #1444-D (#21462)

Wentao Ye committed over 1 year ago

[Bugfix][PD] set max_completion_tokens=1 if req has this value (#21841)

Abirdcfly committed over 1 year ago

feat(multimodal): Add customizable background color for RGBA to RGB conversion (#22052)

Gamhang committed over 1 year ago

[Bugfix] Check NVIDIA artifactory is accessible before using flashinfer cubin kernels (#21893)

Michael Goin committed over 1 year ago

Fix `get_kwargs` for case where type hint is `list[Union[str, type]]` (#22016)

Harry Mellor committed over 1 year ago

[BUG] [ROCm] Fix import bug on ROCm (#22083)

TJian committed over 1 year ago

[Speculative Decoding] Add `speculators` config support (#21345)

Dipika Sikka committed over 1 year ago

Revert "Update sampling_metadata.py (#21937)" (#22088)

Harry Mellor committed over 1 year ago

[Quantization] Enable BNB support for InternS1 (#21953)

Jee Jee Li committed over 1 year ago

[Doc] Added warning of speculating with draft model (#22047)

WeiQing Chen committed over 1 year ago

[Misc] Remove upper bound in openai package version (#22060)

Woosuk Kwon committed over 1 year ago

[Bugfix] Add log prefix in non-dp mode engine core (#21889)

wuhang committed over 1 year ago

[Doc] Add example for Step3-VL (#22061)

Roger Wang committed over 1 year ago

Revert precompile wheel changes (#22055)

Simon Mo committed over 1 year ago