huawei-cloud-modelarts-vllm-ascend-model-deploy指导在华为云 ModelArts 推理平台通过 vLLM-Ascend 推理框架部署开源大语言模型(GLM/Qwen/DeepSeek/Llama 等)为昇腾 NPU 在线推理服务的完整流程。覆盖:确认模型后按 vllm-ascend 社区文档与用户确认部署形式(单机部署/多机部署/PD分离部署 3 种形式,统一单部署单元承载),从 HuggingFace/ModelScope 下载模型权重并上传 OBS、从 Quay.io 拉取 vllm-ascend 镜像并推送 SWR、按确认的部署形式选用专用脚本模板(单机/多机/PD 三套,脚本内不做部署形式运行时分支)生成启动/探针/角色识别脚本并上传 OBS、按 ModelArts 平台适配要点(端口 8080、OBS 挂载、bash 数组、探针命令检查、超节点亲和组)通过新版在线服务部署(二选一: 方式A 调用 CreateInferService API(POST /v2/{project_id}/services)自动部署 / 方式B 在 ModelArts 控制台按一步步点击指导手动部署;不再创建 AI 应用——该模块已废弃)、通过 OpenAI 兼容 API 调用验证。Triggers include: "ModelArts 部署大模型/开源模型", "vllm-ascend", "昇腾 NPU 推理", "HuggingFace/ModelScope 模型上云", "OBS/SWR 镜像迁移", "大模型在线服务", "多机部署", "多副本部署", "PD 分离部署", "超节点亲和组", "新版在线服务", "CreateInferService", "控制台手动部署在线服务"。当用户提到以上任一场景时都应使用本技能,即使没有明确说出'部署'二字。
Install via ClawdBot CLI:
clawdbot install huaweicloudskill/huawei-cloud-modelarts-vllm-ascend-model-deployLoading skill content… the page will refresh in a moment.
Usage Guide
Loading usage data… refresh in a few seconds.
Control remote Windows machines via SSH. Use when executing commands on Windows, checking GPU status (nvidia-smi), running scripts, or managing remote Windows systems. Triggers on "run on Windows", "execute on remote", "check GPU", "nvidia-smi", "远程执行", "Windows 命令".
Perform reverse lookup of gTLD domains hosted on a specified nameserver with optional filters by TLD and domain prefix length.
Essential curl commands for HTTP requests, API testing, and file transfers.
Connect to remote desktops via RDP, VNC, and SSH X11 with secure tunneling and troubleshooting.
Monitor web pages for content changes and get alerts. Track URLs, detect updates, view diffs. Use when asked to watch a website, track changes on a page, mon...
Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup, infrastruc...