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
- [Core] Enable LoRA support for classification model
- [Model] Add qwen3-guard model support with streaming input and output.
- [Bug]: FlashInfer autotuning crash with CUDA 13.0
- [Feature]: Fix all of the mypy check
- [Bug]: `vllm bench serve` incorrectly calculates ITL for openai-chat with reasoning, tool calling, or harmony models
- [ROCm][MHA] add dispatch logic for triton and aiter MHA
- [Model][Qwen3VL] Add `torch.compile` support for Qwen3VL
- [WIP] Add general correctness check script for vLLM endpoints
- [WIP] Rebase of https://github.com/vllm-project/vllm/pull/27134 to latest main
- [bugfix]: Fix the issue where unsupported response format types could cause the inference service to crash, enhancing the robustness of vLLM.
- Docs
- Python not yet supported