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][Core] Log KV cache capacity after block-size resolution
- [Kernel][Helion] Optimize fused QK norm RoPE on B200 and H100
- [ROCm] Route sparse-indexer decode top-k through AITER dispatcher
- thinking_token_budget rejected on V2 model runner (''not yet supported'') — port budget logits processor for reasoning-parser models
- [Bug]: gemma4 parser silently ignores named forced tool_choice on 0.26.0 (worked on 0.21.0)
- [Bugfix][Kimi] Enable DeepEPv2 to work with DeepGEMM MXFp4
- [Model][Spec Decode] Tap the pre-norm AttnRes mixture as the Kimi K3 DFlash aux state
- [KVConnector][NIXL] Support attention-HMA layouts in pipeline-parallel push prefill
- [Bugfix][Frontend] Enforce parallel_tool_calls=false in the required-tool grammar
- [Bug]: Inkling tool call leaks as content in multi-turn streaming (turn-initial tool call, tool_calls empty)
- Docs
- Python not yet supported