[Observability] log sub process killing in process manager force kill (#52314)

Ning Xie committed 22 days ago

[Core] Bound UniProc EngineCore startup threads to available CPUs (#58946)

Andreas Karatzas committed 22 days ago

[CPU][Whisper] Support W4A16 quantized Whisper on the CPU WNA16 kernel (#58268)

Harshal Adhav committed 22 days ago

[Bugfix][Frontend] Constrain forced named tool choice with empty parameters to a JSON object (#45290)

Ting SUN committed 22 days ago

[XPU] Use encoder-only model runner for EC producer instances (#59320)

liuzhenwei committed 22 days ago

[Bugfix][Model] Fix DiffusionGemma silently freezing attention mask under CUDA graph replay (#51994)

Fabian Joswig committed 22 days ago

[Bugfix][Frontend] Report named Anthropic tool calls as tool_use (#47598)

Ting SUN committed 22 days ago

[Bugfix][Frontend] Ignore reused prompt token ids for media in /v1/responses (#59173)

Shijie Lyu committed 22 days ago

[Agents] Add API compatibility checking skill (#58003)

Flora Feng committed 22 days ago

[Refactor] Remove dead tests code (#58916)

Wentao Ye committed 22 days ago

[Bugfix][HiSparse] Never allocate GPU pages without host backing (#59036)

Lucas Wilkinson committed 22 days ago

[Bugfix][CPU][DiffusionGemma] Support narrower canvas w/ sync scheduling (#59107)

Mia Ojeda committed 22 days ago

[Benchmark] Add sweep warmup and failure recovery (#57305)

Louie Tsai committed 22 days ago

support rl feature : weight checker (#51350)

shiyuan680 committed 22 days ago

[Bugfix][MiniMax M3] Share target embeddings with MTP under PP (#58648)

xiaozhoupy committed 22 days ago

[Bugfix][HiSparse] Resolve MTP verification rows with a union residency kernel (#59235)

Matthew Bonanni committed 22 days ago

[CI] Fix mock type narrowing in LoRA serving test (#59344)

Kevin H. Luu committed 22 days ago

[Dependency] Upgrade FlashInfer to 0.7.0.post1 (#59323)

Wei Zhao committed 22 days ago

[Rust Frontend] Use the MiMo structural-tag builder (#59148)

Bugen Zhao committed 22 days ago

[Bugfix][Frontend] Reject LoRA adapters named after a served model (#59286)

Nick Hill committed 22 days ago