[Bugfix] Fix for issue 17396 (#18773)

Fred Reiss committed over 1 year ago

[FEAT][ROCm] Add AITER grouped topk for DeepSeekV2 (#18825)

vllmellm committed over 1 year ago

[BugFix] Pydantic part 2 (#18911)

Luka Govedič committed over 1 year ago

[doc] fix the list rendering issue - security.md (#18982)

Reid committed over 1 year ago

[Neuron] Add Multi-Modal model support for Neuron (#18921)

Satyajith Chilappagari committed over 1 year ago

fix security issue of logging llm output (#18980)

Lucia Fang committed over 1 year ago

[Bugfix]: Fix the incompatibility issue with Structured Outputs when Thinking is disabled (#18879)

Chauncey committed over 1 year ago

[Misc] Fix estimated max model len msg (#18966)

Yong Hoon Shin committed over 1 year ago

[Frontend] Add rerank support to run_batch endpoint (#16278)

Pooya Davoodi committed over 1 year ago

create util function for batched arange (#18937)

Yu Guo committed over 1 year ago

[Docs] Correct multiprocessing design doc (#18964)

Lukas Geiger committed over 1 year ago

Tool parser regex timeout handling (#18960)

Will Eaton committed over 1 year ago

[Misc] add group_size is -1 in awq quantization (#18910)

rongfu.leng committed over 1 year ago

[VLM] Add PP support and fix GPTQ inference for Ovis models (#18958)

Isotr0py committed over 1 year ago

Benchmark script for fp8 vs bf16 gemm (#17126)

Michael Goin committed over 1 year ago

[Perf] API-server scaleout with many-to-many server-engine comms (#17546)

Nick Hill committed over 1 year ago

Improve "failed to get the hash of the compiled graph" error (#18956)

Richard Zou committed over 1 year ago

[Docs] Update SECURITY.md with link to our security guide (#18961)

Russell Bryant committed over 1 year ago

[doc] show the count for fork and watch (#18950)

Reid committed over 1 year ago

[Feature] minicpm eagle support (#18943)

Shawn Huang committed over 1 year ago