Pin Ray version to 2.40.0 (#13490)

Woosuk Kwon committed over 1 year ago

[V1] Optimize handling of sampling metadata and req_ids list (#13244)

Nick Hill committed over 1 year ago

[V1][Tests] Adding additional testing for multimodal models to V1 (#13308)

Murali Andoorveedu committed over 1 year ago

[misc] fix debugging code (#13487)

youkaichao committed over 1 year ago

[V1][PP] Enable true PP with Ray executor (#13472)

Woosuk Kwon committed over 1 year ago

[CI/Build] migrate static project metadata from setup.py to pyproject.toml (#8772)

Daniele committed over 1 year ago

[Bugfix] Fix invalid rotary embedding unit test (#13431)

Liangfu Chen committed over 1 year ago

[Bugfix] Handle content type with optional parameters (#13383)

zifeitong committed over 1 year ago

[ROCm] Make amdsmi import optional for other platforms (#13460)

Cyrus Leung committed over 1 year ago

[Bugfix] Remove noisy error logging during local model loading (#13458)

Isotr0py committed over 1 year ago

[Doc]: Improve feature tables (#13224)

Harry Mellor committed over 1 year ago

[Bugfix] Fix failing transformers dynamic module resolving with spawn multiproc method (#13403)

Isotr0py committed over 1 year ago

[Bugfix] Ensure LoRA path from the request can be included in err msg (#13450)

Yuan Tang committed over 1 year ago

Add outlines fallback when JSON schema has enum (#13449)

Michael Goin committed over 1 year ago

[V1][PP] Fix & Pin Ray version in requirements-cuda.txt (#13436)

Woosuk Kwon committed over 1 year ago

[Quant] Aria SupportsQuant (#13416)

Kyle Sayers committed over 1 year ago

[core] fix sleep mode in pytorch 2.6 (#13456)

youkaichao committed over 1 year ago

[Bugfix] Only print out chat template when supplied (#13444)

Yuan Tang committed over 1 year ago

[Quant] Arctic SupportsQuant (#13366)

Kyle Sayers committed over 1 year ago

[Quant] Molmo SupportsQuant (#13336)

Kyle Sayers committed over 1 year ago