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
- Add mixed serving boundary benchmark
- Add extensible engine core outputs for OOT backends
- [Bug]: Kimi K2 - stream_interval 4 + kimi_k2_reasoning_parser
- [Bug][ROCm][gfx1151] sampler.cu: topKPerRowDecode<1024> exceeds local memory limit on Wave32 GPUs
- [RFC]: A registry + CI ratchet so tuned Triton kernel configs cannot silently rot
- [Misc] Add test suite for PoolsideV1ReasoningParser
- Mxfp8 mtp triton tile tuning
- [Frontend] [Parser] Port DeepSeek V4 to streaming parser engine framework
- [KVConnector][NIXL] Support pipeline-parallel prefill in push mode
- [Bugfix][Model] Gemma 4: stack variable-length audio clips for multi-audio prompts
- Docs
- Python not yet supported