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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: serve部署模型后,调用chat.completions输入给模型的text中image_pad token被提到了prompt开头
- [Bug]: deepgemm compile error
- [Bug]: 使用vllm+lmcache部署glm4.7,在多并发+长上下文导致服务挂掉
- [Feature]: IndexCache support for DSA models
- [Feature]: add ParoQuant quantization
- [Bug]: Qwen3.5-122B-A10B-FP8 EngineCore crash on concurrent image requests
- [bug fix] not override "partial_rotary_factor" if it is in model config
- [Bug]: key error: ‘Layer.34.mlp.experts.gate_up_proj’
- [P/D] [MooncakeConnector] layerwise push prototype
- [Bugfix] Fix bogus "Loading weights took" time in DefaultModelLoader
- Docs
- Python not yet supported