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
- [Bug] gemma4 tool parser, no reasoning parser, request without tools: streamed content ends with stripped `<|channel>`/`<channel|>` since #47562
- [Bug]: Claude Code tool search: first request of every session rejected with 400 (tool_addition content blocks not accepted by /v1/messages)
- [CI] Split (H200 MIG 35GB / MI355) PyTorch Fullgraph into named jobs
- [Bugfix][Core] Raise a fresh EngineDeadError per request instead of re-raising the shared instance
- [Spec Decode][dflash] Drafter KV group is never identified, so prefix-cache reuse is silently disabled for the Mamba groups
- [Bugfix][ROCm] Handle MoE padding sentinel in AITER fused experts
- [Bugfix][MRV2][Spec Decode] Honor dynamic K in autoregressive speculators, 1.2~1.3x kernel perf improvement
- [Perf] Optimize Molmo2 pooling preparation
- [Bugfix] Drop unhonored SupportsPP on Glm5NextForCausalLM
- [Bugfix] Honor DeepSeek-V4 enable_thinking precedence
- Docs
- Python not yet supported