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
- fix: skip torch.compile for DeepSeek V3.2 tokenizer to avoid MLIR error on H20 GPUs (closes #44949)
- fix: correct torch dependency removal logic in use_existing_torch.py (closes #42363)
- [Bugfix] Quiet weight prefetch logs during shutdown
- [Attention][DSA][DCP] Support DCP for DeepSeek Sparse Attention
- [Bug]: OTEL "Dynamo bytecode transform" span reports wildly incorrect duration (tens of thousands of days)
- [MoE] Enable DeepSeek V4 EPLB across platforms
- Fix MoE kernel bounds checks
- Fix Qwen3-Omni audio-in-video image/video merge crash
- [Bugfix][V1] Warm up KV block zeroing before JIT monitor
- [Doc] add AFK integration
- Docs
- Python not yet supported