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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Build] pin build docker to v2.11.0-rc6
- [Bug]: Pixtral model(Migstral-Small-2509) will raise AttributeError NoneType Size on graph mode. Eager mode is ok
- [Bug]: vLLM 0.21: DeepSeek-V4-pro crashes with tensor size mismatch & CUBLAS error during PP+TP inference on 2x8 H800
- [Feature]: Integrate FlashQLA for fast linear attention
- Granite 3.3 8B / 4.0 H-Small tool calls not parsed into OpenAI-compatible format
- [Bug]: worker process remains after SIGKILL the serve process for Qwen3omni model
- [CI Failure]: Language Models Tests (Hybrid) 1 - granite-4.0-tiny-preview prefix caching regression
- [Bug]: Fix two crashes that prevent DeepSeek-V4-Flash + OffloadingConnector
- [CI Failure]: Acceptance length issue in the Speculators Correctness group
- [ROCm] Cpu offload for ROCm 7.13+ to align the hipMemcpyBatchAsync params
- Docs
- Python not yet supported