Repository navigation
docs(flash): explain standby workers next to the workers parameter - #902
Open
justinwlin wants to merge 1 commit into
Open
justinwlin wants to merge 1 commit into
justinwlin wants to merge 1 commit into
Conversation
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Automations to automatically generate PRs for you. |
3 tasks done
justinwlin
force-pushed
the
docs/flash-workers-standby
branch
from
October 15, 2026 14:38
4b08b89 to
7672722
Compare
justinwlin
force-pushed
the
docs/flash-workers-standby
branch
from
October 15, 2026 18:32
7672722 to
480f3c4
Compare
This branch was successfully deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds a note under
workersin the Flash parameters reference explainingworkersStandby. Refs runpod/flash#364.Why
A user deployed
workers=(0, 1), sawworkersStandby: 1in the API and workers showing as ready in/health, and concluded scale-to-zero was broken. It isn't. Runpod sets the standby target itself (it's raised based on the max worker count, regardless of what the client sends), fills it with FlashBoot-cached workers, and those don't add compute cost while stopped. The reporter's balance didn't move over ~3 hours. That's the issue's second suggestion: document it next toworkers=.Sending
workersStandbyfrom Flash, as runpod/flash#375 proposed, would have no effect, because the scheduler overrides low values.Verification
endpoint-configurations#flashboot,operation-reference#health,serverless/pricing.validate-tooltips.jsandvalidate-redirect-sources.jspass./health"ready"), then shortened to one plain paragraph.