[Bugfix] Fix quark fp8 format loading on AMD GPUs (#12612)

fxmarty-amd committed over 1 year ago

[TPU] Fix the test_sampler (#17820)

Jevin Jiang committed over 1 year ago

[Bugfix] Fix tool call template validation for Mistral models (#17644)

Rick Yuan committed over 1 year ago

[Misc] support model prefix & add deepseek vl2 tiny fused moe config (#17763)

xsank committed over 1 year ago

[Bugfix] Fix bad words for Mistral models (#17753)

Qiong Zhou Huang committed over 1 year ago

[Qwen3]add qwen3-235b-bf16 fused moe config on A100 (#17715)

Ximingwang-09 committed over 1 year ago

[Frontend] Chat template fallbacks for multimodal models (#17805)

Cyrus Leung committed over 1 year ago

[Hardware][Intel-Gaudi] Support Automatic Prefix Caching on HPU (#17648)

Agata Dobrzyniewicz committed over 1 year ago

[Hardware][Power] Enable compressed tensor W8A8 INT8 quantization for POWER (#17153)

Akash kaothalkar committed over 1 year ago

[Kernel][Hardware][AMD] Bf16 mfma opt for ROCm skinny GEMMs (#17071)

Hashem Hashemi committed over 1 year ago

[V1] Add VLLM_ALLOW_INSECURE_SERIALIZATION env var (#17490)

Russell Bryant committed over 1 year ago

Only log non-default CLI args for online serving (#17803)

Harry Mellor committed over 1 year ago

[Installation] OpenTelemetry version update (#17771)

Mikhail Podvitskii committed over 1 year ago

Improve exception reporting in MP engine (#17800)

Vadim Markovtsev committed over 1 year ago

[Core] Support full cuda graph in v1 (#16072)

Chanh Nguyen committed over 1 year ago

[BugFix] Fix `--disable-log-stats` in V1 server mode (#17600)

Nick Hill committed over 1 year ago

Don't call the venv `vllm` (#17810)

Harry Mellor committed over 1 year ago

[Chore][Doc] uses model id determined from OpenAI client (#17815)

Aaron Pham committed over 1 year ago

[Core][Feature] Input metadata dump on crash (#13407)

Wallas Henrique committed over 1 year ago

[BugFix] Avoid secondary missing `MultiprocExecutor.workers` error (#17811)

Nick Hill committed over 1 year ago