[V1][Minor] Print KV cache size in token counts (#13596)

Woosuk Kwon committed over 1 year ago

Update `pre-commit`'s `isort` version to remove warnings (#13614)

Harry Mellor committed over 1 year ago

[Bugfix] Fix deepseekv3 grouped topk error (#13474)

chenxiaobing committed over 1 year ago

Merge similar examples in `offline_inference` into single `basic` example (#12737)

Harry Mellor committed over 1 year ago

[Kernel] LoRA - Refactor sgmv kernels (#13110)

Varun Sundar Rabindranath committed over 1 year ago

[2/n][ci] S3: Use full model path (#13564)

Kevin H. Luu committed over 1 year ago

[ci] Fix spec decode test (#13600)

Kevin H. Luu committed over 1 year ago

[CI/Build] Use uv in the Dockerfile (#13566)

Michael Goin committed over 1 year ago

[API Server] Add port number range validation (#13506)

Yuan Tang committed over 1 year ago

[ROCm] MI300A compile targets deprecation (#13560)

Gregory Shtrasberg committed over 1 year ago

[Misc] add mm_processor_kwargs to extra_body for Qwen2.5-VL (#13533)

燃 committed over 1 year ago

[Misc] Warn if the vLLM version can't be retrieved (#13501)

Alex Brooks committed over 1 year ago

[bugfix] spec decode worker get tp group only when initialized (#13578)

Simon Mo committed over 1 year ago

[core] add sleep and wake up endpoint and v1 support (#12987)

youkaichao committed over 1 year ago

[ROCm][MoE] mi300 mixtral8x7B perf for specific BS (#13577)

Divakar Verma committed over 1 year ago

[ci] Add AWS creds for AMD (#13572)

Kevin H. Luu committed over 1 year ago

[Misc] Qwen2.5 VL support LoRA (#13261)

Jee Jee Li committed over 1 year ago

[3/n][CI] Load Quantization test models with S3 (#13570)

Kevin H. Luu committed over 1 year ago

[BugFix] Avoid error traceback in logs when V1 `LLM` terminates (#13565)

Nick Hill committed over 1 year ago

[Misc] Avoid calling unnecessary `hf_list_repo_files` for local model path (#13348)

Isotr0py committed over 1 year ago