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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [GLM-5.3-Flash] Rework kpool compress and dual-stream indexer scheduling
- feat(mla-prefill): let FlashInfer serve (256,256) MLA prefill via backend="auto"
- [ROCm][AMD] GLM5.2/5.3 Performance Optimization on gfx950 / MI355X
- [Bugfix][Frontend] Support scalar priority and wire priority into LLM.chat()
- [LoRA] Add DeepSeek V4.1 text and vision adapter support
- [Doc] Add AISIX AI Gateway integration guide
- [Bug]: audio/transcriptions verbose_json segment ids are not unique
- [Bug][Reasoning] kimi_k3: non-streaming path classifies truncated reasoning as content (inconsistent with streaming path)
- [Model][Perf] Add LLaVA-OneVision encoder CUDA graph support
- Fix XPU WNA16 UVA offload materialization
- Docs
- Python not yet supported