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 supported15 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: vllm0.11.0 启动 qwen3-vl 服务,显存不释放,导致 OOM
- [RFC]: Deprecate Legacy Quantization Formats
- [Feature] add manual numa binding
- [1/n] Migrate activation kernels to libtorch stable ABI
- add fireredasr model
- [Bug]: [gpt oss 20b] [tool_call] Unexpected token 12606 while expecting start token 200006
- [Bug] Fix gpt-oss missing tool content
- Add plugin registry and callbacks for AI model validation
- [Performance]: Deepseek-V3 Performance Uplift Plan on ROCm Backend
- [Bug]: Hybrid Attention models broken after switching to flashinfer 0.4 (tested on Granite 4.0 H, Qwen3-Next, Jamba-3B, Nemotron-H-8b)
- Docs
- Python not yet supported