docs(auto-routing): document tier fallback when a tier cannot serve - #726
Open
tin-berri wants to merge 2 commits into
Open
docs(auto-routing): document tier fallback when a tier cannot serve#726tin-berri wants to merge 2 commits into
tin-berri wants to merge 2 commits into
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
5 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Documents the tier fallback ladder added in BerriAI/litellm#35331
A classified tier used to resolve to whatever the config named, whether or not the router could serve it, so an unregistered model group or one entirely in cooldown failed the request. Resolution now walks live models in the classified tier, then upward a tier at a time, then
default_model, then the classified tier as a best effort; never downward. Adds the section explaining the order, thetier_fallback_fromfact recorded when it climbs, and the two cases that still raise rather than being routed around (an empty tier pool, and a routing plugin narrowing a tier to zero)