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 supported44 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [CI/Build] Make opencv-python-headless an optional dependency
- [Feature]: Support NixlConnector with Pipeline Parallelism for disaggregated serving
- [RFC] Support Intel Quantization Toolkit AutoRound on Intel Platforms
- [Bug]: Gemma-4 fails when forcing FLASHINFER attention backend on Blackwell SM120 (head_size not supported)
- [Bug]: Max token length incorrect when /nothink tag on Qwen3.5-4B
- [Feature]: Prefix caching completely ineffective for Mamba-hybrid models (Qwen3.5) when prompt < block_size (528 tokens)
- [Bug]: Scheduling deadlock in _mamba_block_aligned_split with multiple large multimodal inputs on hybrid Mamba models
- [Kernel][MoE] Add H200 tuned config for Gemma4 MoE on TP=8/4/2/1
- [Kernel] Add FlashInfer mm_bf16 as a backend
- [codex] Ignore empty connector-polling profiling steps
- Docs
- Python not yet supported