메뉴
Scaffold a new KServe model server from scratch — create the model.py, Blubber config, Docker Compose service, pipeline config, and CI wiring. Use when the engineer wants to add a new inference service model to this repo.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/wikimedia/machinelearning-liftwing-inference-services --skill add-model명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Triage Wikimedia ML inference-services incidents at a time T (now or past). TRIGGER on "investigate / triage / debug / post-mortem / what happened" when the subject is a LiftWing alert, ML-serve namespace, error spike, latency regression, or pod crash — including generic phrasing ("investigate this issue") when context (Phabricator task, pasted alert, log snippet) points at LiftWing, even with no alert string. Always trigger on: LiftWingServiceErrorRate, KubernetesDeploymentUnavailableReplicas, KubernetesPodCrashLooping; any namespace under revscoring*, revertrisk*, articletopic-outlink, or other ML-serve; clusters ml-serve-eqiad, ml-serve-codfw, ml-staging-codfw. SKIP only when modifying code without diagnosing a runtime incident. Pulls Prometheus via Grafana's anonymous datasource proxy; correlates with Gerrit merges in `inference-services` and `deployment-charts` (Phab IDs from `Bug:` footers). Read-only.
Analyze a model server's Python code and its deployment chart to identify performance bottlenecks and optimization opportunities for CPU and GPU (AMD MI300X, ROCm, vLLM) inference services on KServe. Use when you want to improve inference throughput or latency for a model.
Scaffold a new LiftWing ML service in operations/deployment-charts. Handles both adding to an existing namespace (append inference_services entry) and creating a brand-new namespace (full helmfile scaffold). Use when an engineer wants to deploy a new inference service for the first time.
SKILL.md 표시 중
SOC 직업 분류 기준
| name | add-model |
| description | Scaffold a new KServe model server from scratch — create the model.py, Blubber config, Docker Compose service, pipeline config, and CI wiring. Use when the engineer wants to add a new inference service model to this repo. |
| argument-hint | [model-name] |
| allowed-tools | ["Bash(mkdir *)","Bash(cp *)","Read","Write","Edit","Glob","Grep"] |
Scaffold all the files needed for a new model server.
src/models/<name>/model_server/ directory.src/models/<name>/model_server/model.py — subclass kserve.Model with load(), preprocess(), predict(), and a if __name__ == "__main__" block that reads MODEL_NAME and MODEL_PATH from the environment and starts kserve.ModelServer().start([model]). Reference an existing model like revert_risk_model for the pattern.src/models/<name>/model_server/requirements.txt with the model's Python dependencies. The shared python/requirements.txt is always installed alongside.blubber.yaml to .pipeline/<name>/. Use a CPU model (e.g., revertrisk/revertrisk.yaml) as the template unless this model needs a GPU/pyTorch base image.docker-compose.yml: platform: linux/amd64, build from .pipeline/<name>/blubber.yaml, expose port 8080, set MODEL_NAME, mount /mnt/models/ from a PATH_TO_<NAME>_MODEL env var..pipeline/config.yaml: a <name> pipeline (test + production stages) and a <name>-publish pipeline (publish to registry).test/unit/<name>/.integration/config repo: jjb/project-pipelines.yaml and zuul/layout.yaml.Makefile.https://analytics.wikimedia.org/published/wmf-ml-models/.python/ (decorators, preprocess utils, metrics) is available to all models..env file locally with PATH_TO_<NAME>_MODEL pointing to downloaded model files.$ARGUMENTS — the model name in kebab-case (e.g., article-quality, revert-risk-wikidata).