Fix quantized_matmul with 4D inputs #4335
Closed
Conversation
This file contains 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
Summary: MobileBERT has a matmul with 4D inputs (`[1, 4, 8, 32]` by `[1, 4, 32, 8]`) which is unsupported. The fp32 kernel _can_ run it though, resulting in an error. This diff fixes the meta kernel to handle cases where the leading dimensions are more than one (the kernel itself can already handle it!). Also move the exported graph dump to `export_program`, where it belongs. This prevents some double printing in some cases. Differential Revision: D60050087
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/4335
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 3bc88a8 with merge base 6dbb4dc ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D60050087 |
dulinriley
approved these changes
Jul 22, 2024
|
This pull request has been merged in f0364e8. |
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Outdated suggestions cannot be applied.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.
Summary:
MobileBERT has a matmul with 4D inputs (
[1, 4, 8, 32]by[1, 4, 32, 8]) which is unsupported. The fp32 kernel can run it though, resulting in an error.This diff fixes the meta kernel to handle cases where the leading dimensions are more than one (the kernel itself can already handle it!).
Also move the exported graph dump to
export_program, where it belongs. This prevents some double printing in some cases.Differential Revision: D60050087