[Kernel][Bugfix] Fixup some warnings in nvfp4_blockwise_moe when CUDA < 12.8 (#20324)

Tyler Michael Smith committed over 1 year ago

Enable group size 64 for Machete (#20290)

czhu-cohere committed over 1 year ago

[Refactor] Refactor import utils (#20269)

Wentao Ye committed over 1 year ago

remove unused variables in marlin_template.h (#20236)

周周周 committed over 1 year ago

[Optimization] Cache sampled token ids in model runner (#20291)

Woosuk Kwon committed over 1 year ago

[V1] [ROCm] Enable EP with AITER Fused MoE (#20270)

TJian committed over 1 year ago

[Frontend] Expand tools even if tool_choice="none" (#17177)

Shintarou Okada committed over 1 year ago

[CUDA graphs] Enable full cuda graphs with FA3 AoT scheduling (#20301)

Woosuk Kwon committed over 1 year ago

[Docs] Update transcriptions API to use openai client with `stream=True` (#20271)

Nicolò Lucchesi committed over 1 year ago

[Misc] Minor refactoring for scheduler (#20299)

Woosuk Kwon committed over 1 year ago

[Model]Add Tencent HunYuanMoEV1 Model Support (#20114)

aiyiwang2025 committed over 1 year ago

Add GLM4.1V model (Draft) (#19331)

Yuxuan Zhang committed over 1 year ago

[Misc] Minor refactor of NIXL background handshake (#20068)

Nicolò Lucchesi committed over 1 year ago

[Quant] [Bugfix] Fix quantization config matching with `hf_to_vllm_mapper` (#20046)

Kyle Sayers committed over 1 year ago

[Perf] Validate @config in pre-commit instead of dynamically (#20200)

Lionel Villard committed over 1 year ago

[doc] fix the incorrect logo in dark mode (#20289)

Reid committed over 1 year ago

[BugFix][V1][ROCm] Triton MLA uses V0 backend on V1 engine (#19067)

TY-AMD committed over 1 year ago

[Misc] remove redundant char (#20287)

Kebe committed over 1 year ago

[Bugfix] Fix deepep tests (#20288)

Varun Sundar Rabindranath committed over 1 year ago

[CPU] Update custom ops for the CPU backend (#20255)

Li, Jiang committed over 1 year ago