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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Consolidate ZMQ context manager
- [Bug]: Regression in v0.18.0+: This line should not be reached in linear.py when loading nvidia/NVIDIA-Nemotron-Parse-v1.2
- Skip stop string matching inside <think> blocks
- [Bugfix] DeepSeek V4: recover tool calls within reasoning content
- [Bug]: ROCm MiniMax M3 MXFP8 Disagg not working
- [MM][CG] Add user-configurable global/local token budgets for dual-path ViT CUDA graph
- docs(security): document gRPC interface as insecure for private use only
- add epilogue hook to flex attention
- [Bugfix] Fix hetero TP handshake assertion for GQA-replicated KV heads
- [Doc] Clarify prompt embeds token IDs in offline example
- Docs
- Python not yet supported