Warn and ignore typical_p on API requests instead of rejecting them - #18551
Open
SIDDARTHAREDDY8 wants to merge 1 commit into
Open
SIDDARTHAREDDY8 wants to merge 1 commit into
SIDDARTHAREDDY8 wants to merge 1 commit into
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #18542.
PR #18448 made
scheduleRunnerreject any generate/chat request that carriestypical_pwith a 400 ("typical_p is no longer supported"). That breaks existing clients that cannot omit the parameter: e.g. SillyTavern always sendstypical_p(set to the no-op value 1.0), so upgrading to 0.34.1 makes all its generations fail even though the client is not trying to use typical-p sampling.Change:
scheduleRunnernow logs a warning and dropstypical_pfrom the request options instead of failing the request. Model-leveltypical_pvalues stored in existing models are still honored through the model options path, and theollama create/PARAMETER typical_prejection is unchanged (that is a deliberate user action where a hard error is appropriate).Tests:
TestGenerate/ignored_deprecated_option(wasrejected option): a generate request withOptions: {"typical_p": 0.5}now returns 200 instead of 400.go vet ./server/clean;go test ./server/ -run TestGeneratepasses (including the updated subtest and the adjacentnull option is unsetcase). Full./serversuite has one pre-existing failure (TestPullManifestRedirectPolicy) which also fails on the unmodified tree.