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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: EVS for qwen3-vl
- [Bug]: Non-deterministic KV-cache reservation on hybrid GDN model (Qwen3.6) → CUDA-graph capture OOMs after /health passes → restart crash-loop (native full RTX 5090 / sm120)
- [RFC]: vLLM NaN Reporting
- [Bug]: [gpt-oss-120b] tool_choice="required" ignored on /v1/chat/completions (v0.20.1)
- [RFC]: hardware agnostic model definitions in vLLM
- [RFC]: Semantic KV Cache Reuse Interface
- [Kernel] Add optional TileLang backend for bf16 activation-and-mul ops
- fix(scheduler): reject non-positive max_num_scheduled_tokens at construction time
- fix(qwen): implement use_logn_attn for long-context Qwen1 models
- BUG: ValueError too many values to unpack in internlm2_tool_parser when output contains multiple tool-call markers
- Docs
- Python not yet supported