- name
SKILL.md
技能文件保留在发布者的仓库中。
在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add dstackai/dstack --skill dstack-prototyping -a cursor -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add dstackai/dstack --skill dstack-prototyping -a claude-code -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add dstackai/dstack --skill dstack-prototyping -a codex -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add dstackai/dstack --skill dstack-prototyping -a grok -y在 Grok Bot 聊天中发送复制的消息。Bot 会从 GitHub 获取这个 SKILL.md,并添加到你所有 Bot 共享的技能中。
Install this skill: https://github.com/dstackai/dstack/tree/HEAD/skills/dstack-prototyping来自发布者
Use /dstack for CLI commands, YAML fields, apply/attach behavior, service URLs,
and other dstack syntax. This skill explains how to use dstack runs while the
model-serving configuration is still unknown.
Find a working dstack service configuration for the requested model.
Before submitting a service, use a task on real hardware to test the serving image, install/runtime assumptions, model download, cache path, command, port, launch flags, resources, env vars, backend/fleet choice, and local model request. Then submit the same configuration as a service and verify the model through the dstack service URL.
Pick the offer whose hardware best fits the goal at hand. Only when several offers fit comparably, choose a VM-based backend, an SSH fleet, or a Kubernetes fleet: they support idle instances and/or instance volumes, so later runs reuse the provisioned/idle instance or instance volumes for caching model weights (and possibly other writes), while container-based backends start clean on every run.
Fetch https://dstack.ai/docs/concepts/backends.md and classify backends
from the fetched document, not from memory.
If the intention is to use PD disaggregation, the fleet must use placement: cluster. Since PD disaggregation implies running a router, unlike workers that must run on GPUs, the router normally should run on a CPU instance. Use dstack fleet to see existing fleets and dstack fleet get <fleet name> --json to inspect a specific fleet.
Check serving-framework sources early enough to choose the image, command, launch flags, resources, cache paths, request format, and expected model behavior.
For vLLM and SGLang, use these as credible sources:
https://recipes.vllm.ai/ and
https://recipes.vllm.ai/models.jsonhttps://docs.sglang.io/ (fetch /llms.txt for the page
index)https://docs.sglang.io/cookbook/autoregressive/introhttps://github.com/vllm-project/vllm/releases and
https://github.com/sgl-project/sglang/releaseshttps://www.lmsys.org/blog/2026-07-02-agent-assisted-sglang-developmentBefore submitting a service, start a long-lived task:
commands:
- sleep infinity
or an equivalent idle command.
Submit the task detached, attach or SSH into it when available, and run commands inside the live environment. Test the image, installs, model download and cache path, serving command, port, launch flags, local model request, and expected model behavior.
When starting a long-running command in the background from a non-interactive
SSH command, use nohup, redirect stdin from /dev/null, and redirect
stdout/stderr to a log file so the SSH command returns while the process keeps
running. For example (the command can be any long-running command):
nohup vllm serve ... </dev/null > /tmp/vllm.log 2>&1 &
If the image, hardware choice, or major install path changes, submit another task so the changed setup is tested before service verification.
Do not move to a service after checking only GPU visibility, imports, logs, or a health endpoint. Start the server inside the task and send a request that uses the requested model. For a chat or reasoning model, check the response behavior the endpoint is expected to support, such as reasoning output when that model is supposed to expose it.
Follow /dstack structured status guidance when polling task or service status.
After requesting a task or service stop before another submission, wait until
that run reaches a terminal status. This allows dstack to reuse its instance or
instance volumes when available.
Submit the service after the task has verified the configuration: image, command, port, resources, env vars, cache mounts if used, backend/fleet choice, and model request.
Use the service as a duplicate check of the same configuration under dstack service runtime. The model request that worked locally in the task must also work through the dstack service URL.
If service verification fails because the image, install, model download, command, resources, cache, or model behavior needs to change, go back to a task. If the tested serving setup is still right and only the dstack service configuration is wrong, fix the configuration and submit the service again.
If a fleet has placement: cluster and a CPU-only instance, you must use a
configuration with the router on the CPU-only instance, regardless of whether
the workers are aggregated or PD disaggregated.
Whenever possible, connect the workers over gRPC, not HTTP: with a gRPC
router, request parsing, serialization, and tokenization move from the
serving engine to the router, so latency improves just by introducing it.
When using a router:
sleep infinity even when using groups (set it in
each group's commands; top-level commands is not allowed with groups),
and run the actual commands on each node interactively over SSH.https://dstack.ai/docs/concepts/tasks.md
and "Router" in https://dstack.ai/docs/concepts/services.md.If the intention is to use PD disaggregation:
## Router: the router and the prefill/decode workers run as
separate groups, and the fleet needs an interconnect (placement: cluster).https://dstack.ai/docs/concepts/tasks.md and "Replica groups" and
"PD disaggregation" in https://dstack.ai/docs/concepts/services.md.|
---name: dstack-prototypingdescription: |---# skills/dstack-prototyping/SKILL.md常见问题
从发布者处下载 skills/dstack-prototyping/SKILL.md,或复制路径后打开仓库。PlugMCP 只收录该技能,不托管文件。
发布者将它存放在 https://github.com/dstackai/dstack。
Claude、Cursor、Codex 和 Grok Build 可以读取你从发布者仓库添加的 SKILL.md。在聊天中发送技能的 GitHub 文件夹链接,Grok Bot 就会安装它。