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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Frontend] Align hybrid LB mode in server CLI with create_engine_config for headless nodes
- [Bugfix] Skip optional vision import for text-only warmup
- [Rust Frontend][Perf] Reduce per-request output channel memory
- [CI] Re-enable Ascend CI
- [ROCm][MiniMax-M3] Mono decode on the NVFP4 KV and index caches
- [Qwen4Exp] Clean up hybrid cache spec plumbing
- [RFC]: Using Backend-Owned KV Cache Runtime Shapes
- [Feature]: Support simultaneous Tool Calling and Structured Output via Grammar Union / Prefix Tree
- [ROCm][PP] Stage hand-off on SDMA copy engines (--pp-sdma-handoff)
- [Bug]: v0.33.0 GitHub Release incorrectly points to v0.33.0rc3 tag
- Docs
- Python not yet supported