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 supported44 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Gemma-4 + DFlash unservable on Ampere — non-causal + head_dim=256 has no compatible attention backend
- [vLLM IR] Port SiluAndMul
- [Bug]: Per-attention-head quantization is currently available only with the Flash Attention backend and requires the calibration pathway provided by llm-compressor.
- [Waiting on v4 deprecation] Update fast image processing files and classes names after upgrade to Transformers v5
- [Bug]: Gemma 4 fails to initialize with per-token-head KV cache quantization
- [vLLM IR] Port non-silu activations
- [Bugfix][EC Connector] Fix ECExampleConnector load device under TP>1
- [Bug]: TurboQuant `_continuation_prefill` OOMs and kills engine at long-context prefill (~185K actual tokens)
- feat(qwen): register Qwen3_5ForCausalLM and Qwen3_5MoeForCausalLM architectures
- fix: emit response.failed for responses streaming generation errors to avoid Pydantic error explosion
- Docs
- Python not yet supported