fix: use Int4WeightOnlyConfig.group_size in fake quant configs#4518
Open
oriollinan wants to merge 1 commit into
Open
fix: use Int4WeightOnlyConfig.group_size in fake quant configs#4518oriollinan wants to merge 1 commit into
Int4WeightOnlyConfig.group_size in fake quant configs#4518oriollinan wants to merge 1 commit into
Conversation
oriollinan
requested review from
andrewor14,
jerryzh168 and
vkuzo
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/4518
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Following the discussion with @andrewor14 in #3572, this PR updates the
Int4WeightOnlyConfigQAT path to use the configuredgroup_sizeinstead of the hardcoded value128.Previously,
_infer_fake_quantize_configsalways generated fake quantization configs withgroup_size=128, regardless of the value specified inInt4WeightOnlyConfig. As a result, QAT did not honor the configured group size, unlike the corresponding PTQ path.Fixes #3572