docs(routing): requests over a deployment's max_parallel_requests get an immediate 429, no queue - #1513
Merged
Conversation
…llel_requests_queue_size Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Contributor
Author
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
… whole numbers Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
… at startup Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
6 tasks
Contributor
|
bugbot run |
There was a problem hiding this comment.
✅ Bugbot reviewed your changes and found no new issues!
Comment @cursor review or bugbot run to trigger another review on this PR
Reviewed by Cursor Bugbot for commit 0cf07a5. Configure here.
… get an immediate 429, drop the queue size settings Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Documents the behavior change in BerriAI/litellm#41555. A deployment's
rpmortpmderives a per-process concurrency cap (max_parallel_requests, thenrpm, thenint(tpm / 1000 * 6)with a minimum of 1, then the router'sdefault_max_parallel_requests). Until now a request over that cap waited in the proxy for a slot and came back as a slow 200. After the code PR it comes back as an immediate 429 that names the deployment and its cap, raised before any provider callThe Max Parallel Requests section of the routing page now spells out that precedence, states that there is no wait queue and nothing to configure for one, explains that the 429 does not cool the deployment down and that router retries and fallbacks treat it like any other 429 (
num_retries: 0surfaces it to the caller right away), and calls out the change from the earlier queueing behavior together with what to do about it (raise the cap or therpm/tpmit comes from, or handle the 429). A proxy YAML example with anrpm-derived cap and the resulting 429 body, taken from a live proxy on the code PR's tip, round it offThe
default_max_parallel_requests_queue_sizerow an earlier revision of this PR added to therouter_settingsreference inproxy/config_settings.mdis gone again, since the code PR no longer ships a queue or any setting for it.npm run buildcompletes withGenerated static files in "build"Linear ticket
Resolves LIT-7675
Link to Devin session: https://app.devin.ai/sessions/fd9d476571c64999a915a8312aca8389
Open in Devin Desktop: https://app.devin.ai/desktop/session/fd9d476571c64999a915a8312aca8389?variant=devin
Requested by: @yassin-berriai