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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Kernel] Marlin MoE: include SM 12.x in default arch list
- feat(kv-events): emit KV cache metadata
- [DSv4][Nvidia] SM12x DeepSeek V4 support
- [V1] [P/D]Remove per block error handling
- [Bug]: Qwen3-VL-MoE NVFP4 checkpoint (un-BMM'd per-expert format) fails load with IndexError: Dimension out of range
- [Bug]: vLLM v1 with prefix caching: first request differs from subsequent identical requests at temperature=0
- [Installation]: ERROR: Failed building wheel for vllm
- [Roadmap] DeepSeek V4
- [Bug]: IMA in _causal_conv1d_fwd_kernel for long sequence input
- [Bugfix] Skip flashinfer-rope variant in QK norm+RoPE fusion
- Docs
- Python not yet supported