Vllm Installer

This skill should be used when users need to install, configure, debug, or run vLLM inference server on NVIDIA GPUs (especially B200/H100/A100). It covers installation from PyPI or source, dependency management, environment setup, common error diagnosis and fixes, tensor parallelism configuration, and server startup/testing. The skill automatically checks for LSSD mount status and DeepEP installation for MoE models.

yangwhale Updated 15 repo stars

File contents

yangwhale/gpu-tpu-pedia commit a04551eff9 Runs: yangwhale/lssd-mounteryangwhale/deepep-installer

Frequently asked questions

npx get-skill add yangwhale/vllm-installer