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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] fused_qk_norm_rope: partial rotary neox path shuffled from a divergent branch
- [Kernel][torch.compile] CUDA fused QK-norm + RoPE + KV-cache write (fuse_qk_norm_rope_kvcache on FlashAttention)
- [Bugfix][KVConnector] Skip unregistered connectors in MultiConnector stats
- [Question] Support path for platform plugins that cannot install Triton (MRV2 requires it)
- [Bug][Reasoning] kimi_k3: streaming path classifies a response-only completion as reasoning (diverges from non-streaming after #57098)
- [Bugfix][Reasoning] Stream kimi_k3 response-only completions as content
- [Bugfix][Frontend] Accept Anthropic tool_addition and tool_removal content blocks
- [Docs][KV Connector][NIXL] Document stats aggregation semantics (CLI vs Prometheus)
- [Core][Metrics] Add exact recomputed-token counter
- [Bug]: qwen3_coder tool parser drops the last parameter when the model omits </parameter> before </function> (non-streaming {}, streaming unterminated JSON)
- Docs
- Python not yet supported