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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Elastic EP] Clear scaling flag on failure to prevent permane…
- [Core] Extensible (growable) KV cache
- [Bugfix][Frontend] Preserve Kimi native tool-call IDs across Responses API multi-turn round trip (Fixes #50768)
- [Doc] Troubleshooting: add a WSL2 section (pinned memory gates, lingering workers)
- Fix/nixl lease reaper ordering
- [Bugfix][Attention] Size FlashInfer sparse MLA workspace for decode-context-parallel
- [Bug]: OverflowError crash in `prompt_logprobs` decode path on PD-disaggregated (external KV connector) setup
- [Bugfix][LoRA] Fix Qwen3-ASR audio tower QKV adapters
- [Bugfix][Build] Restore DeepGEMM SM120 support while preserving SITU
- [ROCm][CI] Make image selection content-addressed
- Docs
- Python not yet supported