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

Update ARM CPU experimental kernels from AO to leverage pip install #1458

Open
wants to merge 7 commits into
base: main
Choose a base branch
from

Conversation

metascroy
Copy link
Contributor

  • torchao experimental CPU kernels are now installed and loaded automatically by pip.
  • Switch quantization to use new quantize_ API

@metascroy metascroy requested a review from Jack-Khuu January 15, 2025 21:14
Copy link

pytorch-bot bot commented Jan 15, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchchat/1458

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

❌ 5 New Failures, 2 Cancelled Jobs

As of commit 7707970 with merge base 07768cf (image):

NEW FAILURES - The following jobs have failed:

CANCELLED JOBS - The following jobs were cancelled. Please retry:

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 Meta Open Source bot. label Jan 15, 2025
@Jack-Khuu Jack-Khuu added the Quantization Issues related to Quantization or torchao label Jan 15, 2025
Copy link
Contributor

@Jack-Khuu Jack-Khuu left a comment

Choose a reason for hiding this comment

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

Thanks for making the pip install work with the subclass APIs!!

docs/quantization.md Outdated Show resolved Hide resolved
torchchat/utils/quantize.py Outdated Show resolved Hide resolved
Comment on lines +155 to +157
except Exception as e:
print("Encountered error during quantization: {e}")
print("Trying with PlainLayout")
Copy link
Contributor

Choose a reason for hiding this comment

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

Is there a specific case we are anticipating here?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

If using this on cuda machine of x86 machine

torchchat/utils/quantize.py Outdated Show resolved Hide resolved
@Jack-Khuu Jack-Khuu changed the title update experimental kernels in torchchat Update ARM CPU experimental kernels from AO to leverage pip install Jan 15, 2025
@Jack-Khuu
Copy link
Contributor

cc: @manuelcandales

Can have please for MPS? 🥺🥺 (Separate PR)

@Jack-Khuu
Copy link
Contributor

Awaiting pytorch/executorch#7759

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 Meta Open Source bot. Quantization Issues related to Quantization or torchao
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants