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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Frontend] Load tool/reasoning parser plugins in run-batch
- [Bugfix][GPT-OSS] Scope engine-level structured outputs to Harmony final channel
- [Bugfix][Tool Calling] Fix doom loop with strict-mode empty-argument tools
- [Bugfix][MiniMax-M3] Recover tool-call params when opening tag is elided
- [Test][CPU] Cover native slot-mapping fallback in CPU CI
- [Bugfix][Spec Decode] Preserve target-only tokens with narrower draft vocabularies
- [ROCm][Model][BugFix] Fix DiffusionGemma hang with TP4 with AITER on or with AITER off while another process uses GPU memory or intermittently with TP8
- [EP] Bound NIXL EP dispatch capacity
- [Model] Add native TeleOCR support with a Qwen3 text decoder
- [Bugfix][LoRA][MoE] Derive the fused MoE LoRA input row from the input shape
- Docs
- Python not yet supported