Add INT16 support to SPACE_TO_DEPTH kernel#6396
Open
nj-1015 wants to merge 1 commit intogoogle-ai-edge:mainfrom
Open
Add INT16 support to SPACE_TO_DEPTH kernel#6396nj-1015 wants to merge 1 commit intogoogle-ai-edge:mainfrom
nj-1015 wants to merge 1 commit intogoogle-ai-edge:mainfrom
Conversation
Add kTfLiteInt16 to the type check in Prepare(). The Eval() function already handles 16-bit data via its TfLiteTypeGetSizeBits case 16 branch. This enables INT16 quantized models (e.g. STATIC_WI8_AI16 from ai-edge-quantizer) to run on the LiteRT runtime.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
kTfLiteInt16to the type check inPrepare()intflite/kernels/space_to_depth.ccEval()function already handles 16-bit data via itsTfLiteTypeGetSizeBitscase 16branch, so no execution logic changes are neededspace_to_depth_test.ccThis enables INT16 quantized models (e.g. STATIC_WI8_AI16 from ai-edge-quantizer) to run on the LiteRT runtime.
Related PR: google-ai-edge/ai-edge-quantizer#445
Test plan
Int16test case following the same pattern as existingint8test