Skip to content
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

Add int4 weight-only embedding QAT #947

Merged
merged 1 commit into from
Oct 1, 2024
Merged

Add int4 weight-only embedding QAT #947

merged 1 commit into from
Oct 1, 2024

Conversation

andrewor14
Copy link
Contributor

@andrewor14 andrewor14 commented Sep 25, 2024

Based on changes in #886 by @TiRune

Copy link

pytorch-bot bot commented Sep 25, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/947

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

✅ No Failures

As of commit cbf980e with merge base 8af72fc (image):
💚 Looks good so far! There are no failures yet. 💚

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

@facebook-github-bot facebook-github-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 Sep 25, 2024
@andrewor14 andrewor14 marked this pull request as draft September 25, 2024 22:57
@andrewor14 andrewor14 changed the title [draft] Add int4 weight-only embedding QAT Add int4 weight-only embedding QAT Sep 30, 2024
@andrewor14 andrewor14 marked this pull request as ready for review September 30, 2024 23:46
Based on changes in D62664322 by Tijmen Blankevoort.
def forward(self, x):
from torchao._executorch_ops import _quantized_decomposed_dequantize_per_channel_group_wrapper
qmin, qmax = _get_qmin_qmax(self.bit_width)
w_dq = _quantized_decomposed_dequantize_per_channel_group_wrapper(
Copy link
Contributor

Choose a reason for hiding this comment

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

is this lowered to executorch?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

yeah

@andrewor14 andrewor14 merged commit 5a4857e into main Oct 1, 2024
17 checks passed
melvinebenezer pushed a commit to melvinebenezer/ao that referenced this pull request Oct 7, 2024
@andrewor14 andrewor14 deleted the embedding-qat branch October 16, 2024 21:05
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.

3 participants