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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Sampling with max_tokens returns result sometimes off by 1 token
- [Bugfix] fix NaiveAll2All incorrect GroupCoordinator usage
- [RFC]: Externally managed elastic EP (decouple from Ray backend)
- [RFC]: Responses API Tools Type Simplification
- [Bug]: Engine stuck at CPU when running long video input on Qwen3-vl model
- Add bias tests for GPT OSS and standardize bias params naming
- [CI][Feature]: Add workflow to make sure PR branch is regularly synced with main
- [Feature][P1]: Remove Duplicate Python Installation
- [Bug]: Qwen3 Omni thinking unstable output
- [Usage]: 启动 qwen3 vl 超级超级超级慢,sglang 启动很快,可能的原因是什么?
- Docs
- Python not yet supported