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]: Reward model usage
- [Feature]: Add support for multi-lora using classification
- [Build] Do not add cmake/ninja dependencies when they are installed
- [Core] Add Additional Metrics to vLLM Server
- vllm-flash-attn build on AMD
- FLOP counting for vLLM inference
- [Bug]: Close feature gaps when using xgrammar for structured output
- [Feature] Support VPTQ quantization
- [MoE][CPU] Extend fused_moe_iterative for non-x86 CPU backends
- [Bug]: Engine is gracefully shutting down
- Docs
- Python not yet supported