Fix guided generation refused after engine load on static-shape engines - #248
Merged
stikves merged 3 commits intoSep 14, 2026
Merged
Conversation
isGuidedGenerationSupported checked loadedEngineIsConstrainedCapable first and returned immediately once non-nil, so the loadedEngineSupportsLogits fallback never ran after an engine loaded. StaticShapeEngine (chunked-static iOS exports) supports logits but isn't ConstrainedGenerationCapable, so guided generation was reported unsupported after the first request even though the executor's guard would have allowed it. Moved the check into InferenceEngine.supportsGuidedGeneration, used by both the executor guard and capability reporting. Fixes apple#247
carinapeng
reviewed
Sep 14, 2026
Covers the second operand of the capability OR: an engine that is ConstrainedGenerationCapable with supportsLogits == false must still report guided generation supported. Reuses MockConstrainedEngine.
tjia1818
approved these changes
Sep 14, 2026
carinapeng
approved these changes
Sep 14, 2026
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
isGuidedGenerationSupportedcheckedloadedEngineIsConstrainedCapablefirst and returned immediately once non-nil, so the loadedEngineSupportsLogitsfallback never ran after an engine loaded.StaticShapeEnginesupports logits but isn'tConstrainedGenerationCapable, so guided generation was reported unsupported after the first request even though the executor's guard would have allowed it.Moved the check into
InferenceEngine.supportsGuidedGeneration, used by both the executor guard and capability reporting.Fixes #247