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
- [Feature][EPLB] Add support for Qwen3 EPLB
- [Bug]: Structured output is not correctly enforced when using GPT-OSS
- [EPLB]: Add EPLB adaptor framework and model register
- [ROCm][torch.compile] Add aiter act/rms+mxfp4 per tensor quant fusion pass for Llama
- [Core][Feat] Add max-waiting-queue-length parameter to reject requests when waiting queue is full
- [Model] Re-support MotifForCausalLM
- [torch.compile] Sequence Parallelism threshold compile ranges
- [ROCm][MXFP4] Enable FP4 MLA BMM support
- [Bug]: Skywork Reward Model series not supported for `llm.reward`
- [ROCm][Quantization] GPT OSS, DS FP4 Upstream fp8 with static scales
- Docs
- Python not yet supported