fixing autoquant bug #265
Merged
fixing autoquant bug #265
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: in some model topographies you see the same weight accessed by multiple modules which caused a bug where weights would get autoquantized multiple times. Also fixed a shape issue with x_scales in some situation with new primitives. Also changed default for autoquant to be interpolation which seems to work better for torchbench benchmarking Test Plan: python test/integration/test_integration.py -k "autoquant" Reviewers: Subscribers: Tasks: Tags:
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/265
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 5f5d175 with merge base 49755f6 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
cpuhrsch
approved these changes
May 23, 2024
dbyoung18
pushed a commit
to dbyoung18/ao
that referenced
this pull request
Jul 31, 2024
Summary: in some model topographies you see the same weight accessed by multiple modules which caused a bug where weights would get autoquantized multiple times. Also fixed a shape issue with x_scales in some situation with new primitives. Also changed default for autoquant to be interpolation which seems to work better for torchbench benchmarking Test Plan: python test/integration/test_integration.py -k "autoquant" Reviewers: Subscribers: Tasks: Tags:
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Outdated suggestions cannot be applied.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:
in some model topographies you see the same weight accessed by multiple modules which caused a bug where weights would get autoquantized multiple times.
Also fixed a shape issue with x_scales in some situation with new primitives.
Also changed default for autoquant to be interpolation which seems to work better for torchbench benchmarking
Test Plan: python test/integration/test_integration.py -k "autoquant"
Reviewers:
Subscribers:
Tasks:
Tags: