vllm
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides documentation and commands for using vLLM, a widely-used and reputable open-source project for high-performance LLM serving.
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
vllmandopenaipackages from the official Python Package Index (PyPI). It also references downloading official model weights from the Hugging Face Hub (e.g., meta-llama, mistralai, google). - [COMMAND_EXECUTION]: Provides standard shell commands for starting the vLLM server via the
python -m vllm.entrypoints.openai.api_servermodule and performing local health checks usingcurl. It also provides a standarddocker runcommand for containerized deployment using the officialvllm/vllm-openaiimage.
Audit Metadata