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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature][Programmatic KV] G1-only Retain via PRIORITY with KvHintEnvelope integration
- Block SSRF in multimodal URL fetching: per-hop validation + address filter
- [Bugfix][Frontend] Validate Anthropic tool choices after tool removal
- [Spec Decode] NemotronH MTP: implement get_top_tokens()
- [Distributed] Route small TP all-gathers through custom_all_gather
- [ROCm][Attention] MXFP4 KV cache with native FP8 x FP4 sparse MLA attention for GLM-5.3-Flash
- [Bug fix]: Fix streaming reasoning detokenization for DeepSeek R1 (by…
- [Bugfix][Tool Parser] Emit FunctionGemma tool calls that arrive in a single streaming delta
- [ROCm] Optimize MiniMax-M3 SwiGLU activation with prefill-gated clamp…
- [Perf][MoE] Fold routed_scaling_factor into output transform weights
- Docs
- Python not yet supported