Check and fix dequantize_affine is idempotent #309
Merged
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/309
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit a064a83 with merge base 88daa1a ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This may result in a performance regression due to the extra copy (even though I'd expect the compiler to handle this). However, the existing implementation can also yield silent correctness issues in case the input is being fed into multiple modules that use this dtype or when using skip connections, etc. |
msaroufim
approved these changes
Jun 3, 2024
dbyoung18
pushed a commit
to dbyoung18/ao
that referenced
this pull request
Jul 31, 2024
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Outdated suggestions cannot be applied.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.
Resolves #289
Follow up includes adding this check for
quantize_affineas well.Follow up includes making tests run on 2.3+ instead of 2.4+ by porting reference into torchao.
Follow up includes deduplicating the test code and creating reference IR to catch compile regressions.