Dstack Prototyping
dstackai/dstackUse with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final dstack service with a model request.
At a glance
Manual install
Python Actively maintained
Install
git clone --depth 1 https://github.com/dstackai/dstack
cp -r dstack/skills/dstack-prototyping ~/.claude/skills/dstack-prototyping
Can use
Not declared by the author
Setup, runtime and requirements describe dstackai/dstack, the repo this skill ships in.
Also in dstackai/dstack
View the repodstack is an open-source control plane for GPU provisioning and orchestration across GPU clouds, Kubernetes, and on-prem clusters.