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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Reject a structured_outputs value that is not StructuredOutputsParams
- [Recipe][ROCm] MiniMax-M3.1-Flash MI355X AgentX PD disaggregation over MoRI-IO
- [Refactor][MoE] Move unquantized backend selection into its oracle
- [Perf][Parser] Skip intermediate argument conversion in buffered parsing
- [Bugfix][Parser] Gemma4: keep tool-call flush beside a partial thought prefix
- [Bugfix] Keep B12X kernels loaded for captured CUDA graphs
- [ROCm] Add a FlyDSL MXFP4 linear backend for RDNA4
- [Prefix Cache] Learn shared Mamba checkpoints for DSpark sibling prompts
- [Bug][ROCm]: ROCM_AITER_MLA can select an aiter MLA decode kernel that silently returns uncorrelated output (gqa_ratio=16, fp8 Q+KV, decode_qlen 3-4, non-persistent)
- [Doc] Fix model implementation guide examples
- Docs
- Python not yet supported