Arm backend: Change _is_ok_for_quantization to support output check #9795
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
_is_ok_for_quantization now checks the node itself as well to verify that the node can be quantized. Previously it was only checked by looking at the inputs to the node. This led to TestSplit failing, which is fixed with the change to `is_non_float_tensor` in `arm_quantizer_utils`, which now handles when node.meta["val"] is a `list` of `FakeTensor`. It traverses the list and checks if any of the elements are **not** a `FakeTensor`. If one element is not a `FakeTensor` the function will return `True`. Change-Id: I898cfea5d02a185fbfa30b18a013123c6d3670a5 Signed-off-by: Sebastian Larsson <[email protected]>
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9795
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 69c7124 with merge base 77c35f5 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Sebastian-Larsson
added
partner: arm
|
From what I can tell the CI failure is unrelated. |
zingo
approved these changes
Apr 1, 2025
kirklandsign
pushed a commit
that referenced
this pull request
Apr 11, 2025
…9795) _is_ok_for_quantization now checks the node itself as well to verify that the node can be quantized. Previously it was only checked by looking at the inputs to the node. This led to TestSplit failing, which is fixed with the change to `is_non_float_tensor` in `arm_quantizer_utils`, which now handles when node.meta["val"] is a `list` of `FakeTensor`. It traverses the list and checks if any of the elements are **not** a `FakeTensor`. If one element is not a `FakeTensor` the function will return `True`. Signed-off-by: Sebastian Larsson <[email protected]>
This was referenced Apr 14, 2025
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.
_is_ok_for_quantization now checks the node itself as well to verify that the node can be quantized. Previously it was only checked by looking at the inputs to the node.
This led to TestSplit failing, which is fixed with the change to
is_non_float_tensorinarm_quantizer_utils, which now handles when node.meta["val"] is alistofFakeTensor. It traverses the list and checks if any of the elements are not aFakeTensor. If one element is not aFakeTensorthe function will returnTrue.cc @digantdesai @freddan80 @per @zingo @oscarandersson8218