Skip to content

replace FbgemmConfig with Int4WeightOnlyConfig #2727

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from

Conversation

namgyu-youn
Copy link
Contributor

@namgyu-youn namgyu-youn commented Aug 10, 2025

Summary:
Resolves the planned update in #2474 (comment) by replacing FbgemmConfig with Int4WeightOnlyConfig.

Test Plan: CI

Copy link

pytorch-bot bot commented Aug 10, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2727

Note: Links to docs will display an error until the docs builds have been completed.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@meta-cla meta-cla bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Aug 10, 2025
@jerryzh168
Copy link
Contributor

oh thanks!

block_size=[1, group_size],
preshuffle=False,
)
base_config = Int4WeightOnlyConfig(group_size=group_size, use_hqq=True)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

need to remove use_hqq and add version=2 for now, we still want to use the fbgemm kernel

base_config = Int4WeightOnlyConfig(group_size=group_size, version=2)

preshuffle=False,
)
quantize_(model, int4_weight_only_config)
use_hqq = "hqq" in quant
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

same here

@jerryzh168
Copy link
Contributor

actually I'll be doing this in my PR

@namgyu-youn
Copy link
Contributor Author

actually I'll be doing this in my PR

Got it, I am fine to close it.

@namgyu-youn namgyu-youn deleted the refactor-awq-example branch August 12, 2025 23:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants