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 supported25 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Automatic test target determination for CI
- [Bug]: Ray Compiled DAG PP channel crashes with AssertionError on concurrent requests (>=2)
- [Bug]: Gemma 4: Engine hang during large prefill caused by Interleaved Attention and p-RoPE implementation
- [Bug]: Engine core initialization failed (Parent process exited) on 2xH100 with Llama-3.3-70B-FP8 (TP/PP=2)
- Shadow mi300 8 test x 5
- [Roadmap] [Draft] vLLM Roadmap Q2 2026
- [RFC]: Support Mooncake Based ECConnector for EPD
- [Frontend] Improve parse_type error message for JSON dict CLI args
- [Bugfix] FlexAttention: reject block_size < 16
- [Bugfix]: gemma4 fix lora online serving
- Docs
- Python not yet supported