[MISC] Logging the message about Ray teardown (#13502)

Cody Yu committed over 1 year ago

Fix copyright year to auto get current year (#13561)

Wilson Wu committed over 1 year ago

[doc] clarify multi-node serving doc (#13558)

youkaichao committed over 1 year ago

[Bugfix] Fix device ordinal for multi-node spec decode (#13269)

shangmingc committed over 1 year ago

[VLM][Bugfix] Pass processor kwargs properly on init (#13516)

Cyrus Leung committed over 1 year ago

[doc] clarify profiling is only for developers (#13554)

youkaichao committed over 1 year ago

[CI/Build] force writing version file (#13544)

Daniele committed over 1 year ago

[Feature] Pluggable platform-specific scheduler (#13161)

Yannick Schnider committed over 1 year ago

[V1][Core] Generic mechanism for handling engine utility (#13060)

Nick Hill committed over 1 year ago

[Model][Speculative Decoding] DeepSeek MTP spec decode (#12755)

Lucia Fang committed over 1 year ago

[Bugfix] Fix Positive Feature Layers in Llava Models (#13514)

Alex Brooks committed over 1 year ago

use device param in load_model method (#13037)

Zhe Zhang committed over 1 year ago

[perf-benchmark] Fix ECR path for premerge benchmark (#13512)

Kevin H. Luu committed over 1 year ago

[1/n][CI] Load models in CI from S3 instead of HF (#13205)

Kevin H. Luu committed over 1 year ago

[Doc] Add clarification note regarding paligemma (#13511)

Roger Wang committed over 1 year ago

[ROCm][MoE configs] mi325 mixtral & mi300 qwen_moe (#13503)

Divakar Verma committed over 1 year ago

[perf-benchmark] Allow premerge ECR (#13509)

Kevin H. Luu committed over 1 year ago

[Hardware][Gaudi][Feature] Support Contiguous Cache Fetch (#12139)

Yu-Zhou committed over 1 year ago

[Misc] Remove dangling references to `--use-v2-block-manager` (#13492)

Harry Mellor committed over 1 year ago

[V1][Spec Decode] Optimize N-gram matching with Numba (#13365)

Woosuk Kwon committed over 1 year ago