vllm-ascend-deploy
OfficialOne-click vLLM deployment on Ascend NPU.
AuthorAscend
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Automates the end-to-end deployment workflow of vLLM on Ascend NPU platforms, eliminating manual steps and reducing risk in complex hardware setups.
Core Features & Use Cases
- End-to-end deployment for vLLM on Ascend hardware (A2/A3) with automated SSH checks, NPU verification, configuration discovery, and user confirmations.
- Cron-based startup monitoring and health validation with automated notifications to keep operators informed.
- Supports models such as Qwen/Qwen3.5, GLM, and other compatible variants, with script-driven container orchestration and validation.
Quick Start
Provide the target model path and deployment environment to start the vLLM deployment flow.
Dependency Matrix
Required Modules
requests
Components
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: vllm-ascend-deploy Download link: https://github.com/Ascend/agent-skills/archive/main.zip#vllm-ascend-deploy Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.