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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- TP > 1 with Ray Serve: Use Multiprocessing Executor (Not Ray Executor)
- [Usage]: Help Running NVFP4 model on 2x DGX Spark with vLLM + Ray (multi-node)
- [Bug]: How to make vLLM support multi stream torch compile and each stream capture cuda graph.
- [Bug]: [TPU] ShapeDtypeStruct error when loading custom safetensors checkpoint on TPU v5litepod
- [Bug]: Incorrect dimension movement in reduce_scatter (first movedim(0, dim) should be movedim(dim, 0))
- [Bug]: EngineCore crashes testing v1/embeddings
- [Bug]: scheduler issue with PD disaggregation
- [Bug] DCP/DBO: 'NoneType' error building attention_metadata during DeepSeek-V3.1 deployment dummy run
- [RFC] DBO fallout tracking metrics
- Add back support of tokenizer_mode == custom
- Docs
- Python not yet supported