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(单节点/多节点/PD分离/PD共置 4 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(单节点/多节点/PD/PD共置 四套,脚本内不做部署形式运行时分支)生成启动/探针/
as observed 2026-10-19T22:50:38.750Z- Identifier
huawei-cloud-modelarts-vllm-ascend-model-deploy- Source
- ClawHub
- Version observed
- 1.0.1
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-10-14T17:39:07.962Z
- Observations recorded
- 2
- Installs (reported upstream)
- 1
- Weekly downloads (upstream)
- 162
- Declared license
- MIT-0
Observation history
2026-10-19T22:50:38.750Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"- 首次发布：指导如何通过华为云 ModelArts 平台和 vLLM-Ascend 推理框架，将开源大语言模型（如 GLM/Qwen/DeepSeek/Llama）部署为昇腾 NPU 在线推理服务。\n- 覆盖从模型选择、权重和镜像准备、部署脚本生成，到新版在线服务部署及 OpenAI 兼容 API 验证的全流程。\n- 支持单节点、多节点、PD 分离和 | "- Removed deprecated skill-card.md, unifying documentation under SKILL.md.\n- Updated artifact-check.md, deployment scripts, and all start script templates to refine artifact vali |
latestVersion |
"1.0.0" | "1.0.1" |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.