This repository was archived by the owner on Jan 30, 2025. It is now read-only.
update checking logic for scale and zp op #83
Merged
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
sjain-stanford
approved these changes
Jul 16, 2024
| op, "Scale operation is not ValueTensorLiteralOp"); | ||
| auto scaleElements = | ||
| dyn_cast<DenseFPElementsAttr>(scaleTensor.getValueAttr()); | ||
| // scale should be a [1] tensor. |
There was a problem hiding this comment.
Let's keep this comment, since it's not immediately apparent (to me) when reading scaleTy.getShape().size() == 1 && scaleTy.getNumElements() == 1.
| op, "Scale operation is not ValueTensorLiteralOp"); | ||
| auto scaleElements = | ||
| dyn_cast<DenseFPElementsAttr>(scaleTensor.getValueAttr()); | ||
| // scale should be a [C] tensor. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
For fake_quantize_ops,
scaleandzero_pointoperands could be lowered byTorchToTcpalready, so we need to relax the checking condition here (just need to make sure the type and shape are valid).