vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Model][Perf] Add LLaVA encoder CUDA graphs for CLIP, SigLIP, and Pixtral
- [ROCm][Perf][GLM-5.3-Flash]: Clean up KDA decode hot path
- [BugFix] Accept hyphenated FunctionGemma tool names in non-streaming parse
- [Bug]: Whisper `verbose_json` silently drops the words after the last complete segment at every chunk cut (long audio); `json`/`text` keep them
- [Attn] Make FlashInfer un-selectable for mixed-causal models
- [Bug]: DiffusionGemma: tensor shape mismatch in post_norm under concurrent decode (inputs_embeds vs silently-clamped sc_embeds)
- [XPU] [bugfix] Unify device visibility handling for XPU and align device ID selection
- [Bugfix][KV Offload] Reset SimpleCPU eager-store placement state on MRV2 resume
- [Bugfix] Fix local-only elastic EP scale-up actor selection
- [Bugfix][MoE] Respect padded row strides in top-k routing
- Docs
- Python not yet supported