vllm-ascend-deploy
昇腾 NPU 平台 vLLM 大模型推理服务一键部署。触发：用户说'部署 模型名'、'NPU 部署模型'、'vllm serve'。流程：SSH检查 → NPU检查 → 配置发现(必须验证) → 用户确认 → 部署 → cron监控 → 验证。约束：(1) 配置必须从官方文档验证，禁止猜测；(2) 后台启动必须用cron监控，禁止手动轮询。支持 Qwen/Qwen3.5、GLM、DeepSeek、Kimi。
Works with
This skill's source license couldn't be confirmed as safe to mirror here, so it isn't inlined. View the full skill directly on its source repository.
View on GitHubMore AI & ML skills
writing-shape
mattpocock/skills
Writing, exploit: shape raw material into an article, paragraph by paragraph.
writing-fragments
mattpocock/skills
Writing, explore: mine raw fragments, no structure yet.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
