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 supported25 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: max-model-len set to 'auto',didn't work. Why?
- [Bugfix] Fix oversized piecewise CUDA graphs for Gemma3n cross-decoder
- [EP] Fault tolerance: automatic elastic scale-down on DP engine death
- [Doc] add Apple Clang 21+ compilation troubleshooting
- [Feature]: Support for transformers>=5.0 in a stable release
- [Bug]: H100 CUDA 13.0 nightly wheels require glibc 2.35 (manylinux_2_35), failing on glibc 2.34 systems
- [Attention] Add head_dim=512 support for FlashInfer trtllm attention backend
- [Bug]: Gemma4 reasoning parser fails to separate reasoning_content — <|channel> tokens stripped before parsing
- [Bugfix] Fix Qwen3 </think> leak in streaming with stop sequences
- [fix]: deepseekv31 tool parser: `"` and `}` may arrive in seperate deltas.
- Docs
- Python not yet supported