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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature] Add GPU UUID support in CUDA_VISIBLE_DEVICES
- [Doc] Add contribution guide for MoE/attention/quantization backends
- Fix dtype detection for local model paths
- [New Model]: microsoft/VibeVoice-ASR support
- [Bug]: MiniMax-M2.1 NVFP4 fails on RTX PRO 6000 Blackwell (SM120) with expert parallel
- [Bug]: "ValueError: No tokenizer file found in directory" when serving Qwen3-Omni
- [Bugfix] Fix empty response under concurrent requests
- [Bug]: LoRA loading fails with Fused MoE when data parallelism (DP > 1) is enabled
- [Bugfix][Tool Parser] Fix crash when parameter description contains parentheses
- [MoE Refactor] Only use RouterMethodType for flashinfer
- Docs
- Python not yet supported