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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix(metrics): fix TPOT accounting for MTP multi-token outputs
- fix: support Qwen3.5 family for DSpark
- [Bugfix][MoE] Plumb swigluoai activation into FlashInfer b12x MoE
- [LoRA] Add DoRA support for serving and linear layers
- [Bugfix] Load per-shard per-tensor FP8 scales for fused GDN in_proj (Qwen3.5/Qwen3-Next)
- [Bugfix] Skip cache-served mm items in tower/connector LoRA mapping
- Add jitter to LoRA adapter_config.json load retries
- [Feature]: Support min_tokens in beam search
- [Core][Model Loader] Enable safetensors auto-prefetch on CephFS
- WorkerProc initialization failure swallows root cause traceback (raise e from None)
- Docs
- Python not yet supported