[Bugfix] Multi-video inference on LLaVA-Onevision (#15082)

Cyrus Leung committed over 1 year ago

[macOS] Ugrade pytorch to 2.6.0 (#15129)

Quang-Linh LE committed over 1 year ago

Fixing Imprecise Type Annotations (#15192)

Wang Ran (汪然) committed over 1 year ago

[release] Tag vllm-cpu with latest upon new version released (#15193)

Kevin H. Luu committed over 1 year ago

[Frontend][Bugfix] support prefill decode disaggregation on deepseek (#14824)

billishyahao committed over 1 year ago

typo: Update config.py (#15189)

Wang Ran (汪然) committed over 1 year ago

Enable CUDA graph support for llama 3.2 vision (#14917)

Matt Ritter committed over 1 year ago

[Doc] Update README.md (#15187)

Cyrus Leung committed over 1 year ago

[Attention] Flash Attention 3 - fp8 (#14570)

Mickaël Seznec committed over 1 year ago

[Misc]fixed disable these http request logs (#14754)

Chauncey committed over 1 year ago

[Doc] Update Mistral Small 3.1/Pixtral example (#15184)

Roger Wang committed over 1 year ago

[Core][V0] Add guidance backend for structured output (#14589)

Russell Bryant committed over 1 year ago

[Benchmark] Allow oversample request in benchmark dataset (#15170)

Jennifer Zhao committed over 1 year ago

[V1][TPU] Support V1 Sampler for ragged attention (#14227)

Nicolò Lucchesi committed over 1 year ago

fix "Total generated tokens:" is 0 if using --backend tgi and --endpo… (#14673)

Wang, Yi committed over 1 year ago

[Bugfix] Fix embedding assignment for InternVL-based models (#15086)

Cyrus Leung committed over 1 year ago

Fix broken tests (#14713)

Jovan Sardinha committed over 1 year ago

[Doc] Clarify run vllm only on one node in distributed inference (#15148)

Rui Qiao committed over 1 year ago

[BugFix] Lazily import XgrammarBackend to avoid early cuda init (#15171)

Nick Hill committed over 1 year ago

[V1] TPU - Tensor parallel MP support (#15059)

Alexander Matveev committed over 1 year ago