Skip to content

docs: Add instant iteration step to Flash quickstart#612

Merged
muhsinking merged 3 commits intomainfrom
promptless/flash-quickstart-reiteration-step
Apr 10, 2026
Merged

docs: Add instant iteration step to Flash quickstart#612
muhsinking merged 3 commits intomainfrom
promptless/flash-quickstart-reiteration-step

Conversation

@promptless
Copy link
Copy Markdown
Contributor

@promptless promptless bot commented Apr 10, 2026

Open this suggestion in Promptless to view citations and reasoning process

Adds a new Step 5 to the Flash quickstart that demonstrates fast re-deployment by guiding users to make a code change and run again, showing the speed difference between first run (30-60s) and subsequent runs (2-3s). Includes idle_timeout=300 (5 minutes) to keep workers running longer before scaling down, giving users more time to iterate on their code.

promptless bot and others added 3 commits April 9, 2026 12:40
Insert new Step 5 demonstrating Flash's fast re-deployment capability by
guiding users to make a code change and run again, showing the speed
difference between first run (30-60s) and subsequent runs (2-3s).
Set idle_timeout=300 (5 minutes) to keep workers running longer
before scaling down, giving users more time to iterate on code
changes and experience the fast re-deployment workflow.
@@ -147,10 +148,27 @@ export RUNPOD_API_KEY="your_key"
Replace `your_key` with your actual API key from the [Runpod console](https://www.runpod.io/console/user/settings).
</Tip>

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added new Step 5 demonstrating instant iteration per Mo King's request to show users how quickly they can re-deploy code (make a change, run it again) before the worker spins down.

Source: https://Team.slack.com/archives/D094WQKSXLK/p1775738158299809

- **`name`**: Identifies your endpoint in the [Runpod console](https://www.runpod.io/console/serverless).
- **`gpu`**: Which GPU to use (`GpuGroup.ANY` accepts any available GPU for faster provisioning).
- **`workers`**: Maximum parallel workers (allows 3 concurrent executions).
- **`idle_timeout`**: Seconds a worker stays active after completing a request before scaling down. Setting this to 300 (5 minutes) gives you more time to iterate on your code while the worker remains warm.
Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Referenced idle_timeout parameter documentation in flash/configuration/parameters.mdx for accurate default value (60s), behavior description, and recommended values (30-300s range).

Source: https://docs.runpod.io/flash/configuration/parameters#idle_timeout

@muhsinking muhsinking self-requested a review April 10, 2026 13:23
@mintlify
Copy link
Copy Markdown

mintlify bot commented Apr 10, 2026

Preview deployment for your docs. Learn more about Mintlify Previews.

Project Status Preview Updated (UTC)
runpod-docs 🟢 Ready View Preview Apr 10, 2026, 1:24 PM

💡 Tip: Enable Workflows to automatically generate PRs for you.

@promptless
Copy link
Copy Markdown
Contributor Author

promptless bot commented Apr 10, 2026

Just a reminder: If you'd like me to act on any feedback you have via Github comments, just type @Promptless in your suggestion and I'll get right on it! (I won't show up in the user dropdown, but I'll process any request that has @Promptless in the comment body.)

@muhsinking muhsinking merged commit 81729e9 into main Apr 10, 2026
2 checks passed
@muhsinking muhsinking deleted the promptless/flash-quickstart-reiteration-step branch April 10, 2026 13:25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant