.claude/skills/huawei-cloud-modelarts-vllm-ascend-model-deployRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
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…
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/huawei-cloud-modelarts-vllm-ascend-model-deployRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/huawei-cloud-modelarts-vllm-ascend-model-deployRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/huawei-cloud-modelarts-vllm-ascend-model-deployRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @huaweicloudskill/huawei-cloud-modelarts-vllm-ascend-model-deployclawhub inspect @huaweicloudskill/huawei-cloud-modelarts-vllm-ascend-model-deploy --version 1.0.6This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
curl -sSL https://cn-north-4-hdn-koocli.obs.cn-north-4.myhuaweicloud.com/cli/latest/hcloud_install.shThis is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:d03cfad12eed9d06eb460cf9a46a3a735f2d2a15920f39e96fd5a193d8448b36references/acceptance-criteria.mdreferences/api-deployment-guide.mdreferences/artifact-check.mdreferences/ascend-hardware-matrix.mdreferences/cli-installation-guide.mdreferences/deployment-form-decision.mdreferences/hixlep-guide.mdreferences/iam-policies.mdreferences/modelarts-console-guide.mdreferences/troubleshooting.mdreferences/verification-method.mdreferences/vllm-ascend-model-doc-guide.mdscripts/a5_hixlep/fix_ub_endpoint.pyscripts/a5_hixlep/gen_route.shscripts/a5_hixlep/generate_ep.pyscripts/a5_hixlep/get_route_eid.pyscripts/a5_hixlep/unofficial_ascend_tools-0.0.7rc4-py3-none-any.whlscripts/check_artifacts.pyscripts/create_infer_service.pyscripts/download_model.pyscripts/get_master_ip.pyscripts/load_balance_proxy_server_example.pyscripts/obs_upload.shscripts/pull_push_image.shscripts/test_inference.pyscripts/upload_code_to_obs.pyskill-card.mdSKILL.mdtemplates/health_check.shtemplates/start_vllm.multi_node.shVersion 1.0.6 expands deployment guidance and support for ModelArts resource pools. - Clarifies flavor selection for dedicated and public resource pools, including proxy sizing for PD deployments. - Updates deployment guides, scripts, and startup templates. - Adds the unofficial Ascend tools wheel. - Removes `skill-card.md`.
Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.
These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.
sha256:a10f487400a94659ec28429be686c9d3d58cefe5c12da5e6166a7ca222c9fb2bsha256:1b72c9a9fd2d3a94887c9dc4bf859b0840244d32b62fefe55f140da042ed6246sha256:55771f52af333cb7825714f2499a62d588862915f566d66e49cb45d5b29b1129sha256:0c2573cca0cc712532aab3e7c10e4285b1f4ad340ffca4b746febb11b33d43a0