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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Expose RequestOutput hook for programmatic use of Serving layer
- [Bug][Docker]: Issues with 0.15.0 and newer docker image when running Qwen3-Next with VLLM_BLOCKSCALE_FP8_GEMM_FLASHINFER=1
- [Model] Add torch.compile support for Ovis2.5 vision encoder
- [Voxstral Realtime] Enable tests
- [CI Failure]: Kernels MoE Test %N
- [Hardware][AMD] Add comments explaining gfx906 (MI50/MI60) is not supported
- [3/N] chatCompletions uses Parser
- try to enable torch.compile for qwen_vl
- Enable torch.compile for OpenGVLab/InternVL3-2B
- [Kernel][perf] optimize NCCL symm_mem vs custom_AR selection thresholds
- Docs
- Python not yet supported