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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: SageMaker Day-0 Compatibility with vLLM
- [Bug]: Sampling with max_tokens returns result sometimes off by 1 token
- [Bug]: Tool use is not supported in Responses API without Harmony None
- [Bugfix] fix NaiveAll2All incorrect GroupCoordinator usage
- [RFC]: Router Registry & Plugin System for vLLM Online Serving
- [Bug]: Kimi Linear KV cache size estimation and usage not making sens
- [RFC]: Externally managed elastic EP (decouple from Ray backend)
- [RFC]: Responses API Tools Type Simplification
- [Performance]: DeepSeek V3 performance drop when enabling MTP on both H200 and MI300X
- [Bug]: Engine stuck at CPU when running long video input on Qwen3-vl model
- Docs
- Python not yet supported