runpod/runpod-plugins-official

runpod-cloud-migrate

Move a workload from another cloud or GPU platform to Runpod: Vast.ai, Lambda, CoreWeave, Paperspace, Modal, Replicate, Baseten, Together AI, Fireworks AI, fal, Hugging Face Inference Endpoints, AWS, Google Cloud or Azure.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/runpod/runpod-plugins-official --skill runpod-cloud-migrate

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Migrate to Runpod from another platform

Moves a project that runs on another cloud or GPU platform onto Runpod. This skill owns the migration procedure and the per-platform maps. It does not own how Runpod works or how to operate it: for those it hands off to the lanes (router).

NeedOwner
What the other platform's thing becomes on Runpodthe platform playbook in reference/ (table below)
Pods vs Serverless, storage, GPU choice, networkingrunpod-usage
Creating and managing Runpod resourcesrunpod-mcp or runpodctl, per the router's matrix
Python apps without a Dockerfile (runpod.App)runpod-flash
A Dockerfile and handler for a custom imagerunpod-build-template
Serving an LLM with an OpenAI-compatible routerunpod-vllm
Ordering, flags and traps for a deploythe golden paths

Rules that hold for the whole migration

  1. Inventory before anything else. Never plan from the user's description alone: the

repo usually depends on more than they remember.

  1. The source platform is read-only until the user says otherwise. List and describe

freely. Never stop, scale down, delete or modify a resource on the source platform without an explicit instruction naming that resource. A migration that breaks production on the old platform before the new one is verified is a failed migration.

  1. Nothing billable on Runpod without an approved plan. Show the plan and an hourly

cost bound first (step 3), then create only what the plan lists.

  1. One workload at a time, smallest first. Verify it with a real request before

starting the next.

  1. Credentials move as secrets, never as text. Carry credential names across. Ask the

user to set values as Runpod secrets or environment variables; do not read a value out of the source platform, print one, or commit one.

  1. Keep the old path callable. Put the new endpoint behind a config switch (an env var

for the base URL or provider) so cutover and rollback are one setting.

  1. State gaps, do not paper over them. Each playbook ends with a "Gaps: stop and ask

the user" section. Those are decisions only the user can make.

  1. The playbooks are a snapshot. Each names the date its platform docs were checked.

Before relying on a detail of the other platform that the migration hinges on, confirm it in that platform's docs or CLI help. For Runpod, the tool in front of you wins (why).

The workflow

1. Inventory

The scanner ships beside this file, in the installed skill directory, not in the user's repo. Resolve it first:

bash
SCAN="$CLAUDE_PLUGIN_ROOT/skills/runpod-cloud-migrate/scripts/scan_cloud_usage.py"
[ -f "$SCAN" ] || SCAN="<directory containing this SKILL.md>/scripts/scan_cloud_usage.py"
[ -f "$SCAN" ] || SCAN=$(find ~/.claude ~/.agents ~/.codex ~/.config -name scan_cloud_usage.py 2>/dev/null | head -1)
python3 "$SCAN" --help >/dev/null || echo "scanner not found: resolve it before continuing"

Then, from the root of the user's repo:

bash
python3 "$SCAN" .            # Markdown summary per platform and kind
python3 "$SCAN" . --json     # every hit, for a large repo

It reads files only: no network, no credentials, no edits. Hits are grouped by kind (sdk, cli, api, config, iac, runtime, credential). A hit is evidence, so open the file before deciding what it means. Show the user the summary table.

The repo is half the picture. Ask the user to run the playbook's "list what's running" commands on the source platform (or run them yourself when its CLI is authenticated and the commands are read-only), because consoles hold resources no file mentions.

No hits means the project deploys by hand or keeps infrastructure code elsewhere. Ask what runs where. Do not guess a platform.

2. Open the playbook for each platform found

PlatformPlaybook
Vast.aireference/vast-ai.md
Lambdareference/lambda.md
CoreWeave, and Kubernetes GPU workloads on any cloudreference/coreweave.md
Paperspace and DigitalOcean GPUreference/paperspace.md
Modalreference/modal.md
Replicate and Cogreference/replicate.md
Baseten and Trussreference/baseten.md
Together AIreference/together-ai.md
Fireworks AIreference/fireworks-ai.md
falreference/fal.md
Hugging Face Inference Endpoints, Spacesreference/hugging-face.md
AWS (EC2, SageMaker, Bedrock, Batch)reference/aws.md
Google Cloud (Compute Engine, Vertex AI, Cloud Run)reference/google-cloud.md
Azure (GPU VMs, Azure Machine Learning, Azure OpenAI)reference/azure.md

Read only the playbooks the inventory calls for. A platform with no playbook still migrates: classify each workload by shape with the table in step 3 and translate from that platform's own docs.

The scanner's openai-compatible rows mark clients that already take a base URL, which makes them a configuration change rather than a rewrite. Its runpod rows mean part of the project is on Runpod already: read those files first and reuse their conventions.

3. Plan, and get the plan approved

Classify every workload by its shape, not by the product name it had:

Workload shapeRunpod target
Calls a hosted model someone else runsA Public Endpoint when Runpod hosts that model, else your own endpoint
Request in, response out, idle between requestsServerless queue-based endpoint
Your own HTTP server, low latency, custom routesServerless load-balancing endpoint
An LLM behind an OpenAI-compatible APIServerless endpoint running the vLLM worker
A job that runs to completion (training, batch)A Pod, or one ephemeral Pod per call from the Runpod SDK
Interactive machine (notebook, SSH, IDE)Pod
Always-on service with a stable addressPod
Multi-node training or HPC with SlurmInstant Cluster

The reasoning behind each row is in runpod-usage concepts.

Write the plan as one table and show it before acting:

ColumnContent
WorkloadName on the source platform, and the files that define it
TargetRow from the table above, and the lane that will create it
ComputeGPU type or pool sized to the model's memory needs, worker bounds
Image and codeReused as is, rebuilt for linux/amd64, or ported (which contract changes)
DataWhat moves, how large, from where to which storage layer
CallersFiles that call the workload and what changes in each
GapsRows from the playbook's gaps section that apply, with the options
Cost boundHourly rate of what will run and for how long during the test

Read live GPU stock before naming a GPU or data center (gpu-selection); stock varies, so the plan names a fallback. Ask the questions the gaps raise in one batch, with the plan in front of the user. Proceed when they approve.

4. Translate (no cloud calls)

Do everything that costs nothing first, on a branch, one commit per workload:

  • Port the container contract or app code using the playbook's code translation section.
  • Rewrite the infrastructure definitions (Terraform, CI deploy steps).
  • Add the config switch for callers (rule 6) and the new credential names.
  • Leave the source platform's files in place. Removing them is the last step.

5. Provision one workload and move its data

Hand off to the lane the plan names, and follow the matching golden path for ordering. Move data before the compute that needs it. Storage placement follows storage: a network volume lives in one data center, so choose the data center from GPU stock and create the volume there.

6. Verify with a real request

A resource that reports ready is not a workload that serves. Send the same input to the old and the new deployment from outside both platforms, then compare: output, latency of a cold and a warm request, and error handling. Use the playbook's "Verify" section for platform-specific checks. Fix and repeat until the outputs agree, then report the numbers.

7. Cut over, then repeat

Switch callers with the config switch. Keep the old deployment running until the user confirms the new one under real traffic. Then return to step 4 for the next workload.

8. Report, and shut the source down only on request

Finish with: what moved, where each thing lives on Runpod (IDs and URLs), what still runs on the source platform, the open gaps, what is billing on Runpod now, and how to roll back. Each platform also has a step-by-step guide for people at https://docs.runpod.io/migrate/<playbook file name without .md>: link it in the report. The playbook's "Shut down" section lists the commands that stop billing on the source platform, including the resources people forget. Offer them. Run one only after the user approves that specific resource.

When the user wants only part of this

The user saysDo
"What would it take to move off X?"Steps 1 to 3, then stop at the plan
"Compare X and Runpod for this project"Steps 1 and 2, then the playbook's product map and gaps. No prices for the other platform: point at both pricing pages
"Port this file"Step 4 for that file, and say which other files the inventory found
"Move our Terraform"Step 1 with attention to iac hits, then the playbook's Terraform rows
"We already moved the compute, fix the callers"Step 1, then the playbook's client and API call map
同じリポジトリから

関連する Skills

すべての Skills
runpod
コミュニティ

runpod

Start here when the Runpod lane is unclear: picks the skill for a task (runpod-mcp and the journey playbooks it routes to, such as runpod-serverless-deploy, runpod-pod-deploy, runpod-pod-doctor and runpod-cost-audit; runpodctl, runpod-flash, runpod-companion-clis, runpod-usage, runpod-templates, runpod-build-template, runpod-migrate, runpod-cloud-migrate) and indexes two dozen end-to-end worked examples (golden paths). Use it before any multi-step or provisioning task, even when the lane is clea

1時間の導入数
3
GitHub Stars
50
更新日
11月19日
runpod
コミュニティ

runpod-build-template

Create or improve a complete Runpod template project from an application request, local code, or GitHub repository, with a documented Dockerfile and app-specific files for Pods or queue/load-balanced Serverless. Use runpod-templates for finding or operating existing official templates, runpod-mcp/runpodctl to register an already-built image as a template, runpod-flash for its code-first workflow, and runpod-companion-clis for standalone image build/push commands.

1時間の導入数
3
GitHub Stars
50
更新日
11月19日
runpod
コミュニティ

runpod-companion-clis

Companion CLIs for Runpod workflows — HuggingFace, GitHub, Docker, and AWS. Use runpod-build-template for complete template project authoring, and the ComfyUI model-repair guide in runpod-templates for imported workflows lacking model download metadata.

1時間の導入数
3
GitHub Stars
50
更新日
11月19日
runpod
コミュニティ

runpod-cost-audit

'Read-only Runpod spend audit: find idle spend, explain serverless billing when nothing seems to run, break spend down by resource type and by resource, and give a whole-account snapshot. Every figure comes from the MCP billing and list reads; it recommends actions and never stops or changes anything. Use when the user asks about their bill, what is costing money, what is running on the account, or tells you to stop or delete idle resources it did not name by id: the audit with ids and the user'

1時間の導入数
3
GitHub Stars
50
更新日
11月19日