[Misc] Remove dead return (#23061)

Woosuk Kwon committed about 1 year ago

[BugFix] Fix for IMA in FA3 varlen combine (#22967)

Lucas Wilkinson committed about 1 year ago

[Misc] fix typo in the multimodal doc (#23051)

Kevinzz committed about 1 year ago

[Bugfix] should use stack instead of concat (#22972)

947132885 committed about 1 year ago

[Kernel] Add cuda kernel for gpt_oss activation (#22951)

Jee Jee Li committed about 1 year ago

[Misc] method name typo fix (#23042)

Ning Xie committed about 1 year ago

[Refactor] Defer tensor data construction in MultiModalKwargs (#23030)

Cyrus Leung committed about 1 year ago

[UX] Separate marlin moe config logic from triton moe (#23006)

Michael Goin committed about 1 year ago

[Bugfix] fix qwen3 moe fp8 accuracy issue (#23031)

Jinzhen Lin committed about 1 year ago

[V1] Logits processors extensibility (#19912)

afeldman-nm committed about 1 year ago

[Kernel/Quant] Remove AQLM (#22943)

Michael Goin committed about 1 year ago

[Flaky CI] Increase timeout tolerance for test_mp_crash_detection+test_default_mm_lora_chat_completions (#23028)

Michael Goin committed about 1 year ago

[Bugfix gpt-oss] Fix float32 convert for flashinfer sink support (#23016)

Michael Goin committed about 1 year ago

[Frontend] Added support for HermesToolParser for models without special tokens (#16890)

Woonggi Min committed about 1 year ago

Fix handling of `max_num_batched_tokens` for pooling tasks (#23004)

Maximilien de Bayser committed about 1 year ago

[New Model]mBART model (#22883)

汪志鹏 committed about 1 year ago

[Refactor] Allow optional MultiModalKwargsItem in IPC (#23022)

Cyrus Leung committed about 1 year ago

Add docs for PrefixRepetitionDataset + enable usage with `vllm bench throughput` (#23012)

Seiji Eicher committed about 1 year ago

[CI][Bugfix] Skip Ovis2 generation test because of broken remote code (#22954)

Isotr0py committed about 1 year ago

[Core] Make cudagraph check cuda platform only (#23005)

Chengji Yao committed about 1 year ago