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 supported51 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Skip cache-served mm items in tower/connector LoRA mapping
- Add jitter to LoRA adapter_config.json load retries
- [Core][Model Loader] Enable safetensors auto-prefetch on CephFS
- WorkerProc initialization failure swallows root cause traceback (raise e from None)
- fix(v1): surface worker init failure root cause to the parent
- [Bugfix][Hardware][XPU] Fix Gemma4 performance regression by allowing platform-native attention
- [BUGFIX] Fix opencua processor on transformers 5
- Fix OOB scale reads in Triton MXFP4 matmul kernel causing NaN outputs
- [RFC]: Port vLLM-built Hopper and Blackwell C++ CUDA kernels to CuTeDSL
- [Bug]: DiffusionGemma output unstable (v0.24.0)
- Docs
- Python not yet supported