[Misc] Delete redundant code (#16530)

Jee Jee Li committed over 1 year ago

[MISC] Make GroupCoordinator compatible with out-of-tree devices (#16464)

Huazhong Ji committed over 1 year ago

[V1] Enable multi-input by default (#15799)

Cyrus Leung committed over 1 year ago

[Misc] Openai transcription client example use same Whisper model (#16487)

Nicolò Lucchesi committed over 1 year ago

[Misc] Update chat utils tests (#16520)

Cyrus Leung committed over 1 year ago

fix: spelling (#16466)

Tianer Zhou committed over 1 year ago

[Frontend] support matryoshka representation / support embedding API dimensions (#16331)

wang.yuqi committed over 1 year ago

[Feature][V1] Add xgrammar to support minLength, maxLength with test (#16516)

leon-seidel committed over 1 year ago

Optimized topk for topk=1 (Llama-4) (#16512)

Michael Goin committed over 1 year ago

[Doc] Update Llama4 Model Names in Supported Models (#16509)

Ye (Charlotte) Qi committed over 1 year ago

[BugFix] Handle non-contiguous tensors properly when serializing (#16492)

Nick Hill committed over 1 year ago

[CI][Bugfix] Add mistral_tool_use to Ci (#16517)

Michael Goin committed over 1 year ago

[Doc] Fix link to vLLM blog (#16519)

Yuan Tang committed over 1 year ago

Bugfix for PixtralHF models without spatial_merge_size (#16513)

Michael Goin committed over 1 year ago

[Bugfix] clean up duplicated code (#16485)

rongfu.leng committed over 1 year ago

Update openai_compatible_server.md (#16507)

Christian Sears committed over 1 year ago

[Kernel] Add tuned FusedMoE kernel config for Llama4 Scout, TP=8 on H100 (#16488)

Yong Hoon Shin committed over 1 year ago

[Frontend] Added chat templates for LLaMa4 pythonic tool calling (#16463)

Ye (Charlotte) Qi committed over 1 year ago

Improve configs - `LoadConfig` (#16422)

Harry Mellor committed over 1 year ago

[Bugfix] handle alignment of encoder_seq_lens in mllama.py (#14784)

Travis Johnson committed over 1 year ago