Skip to content

Qualcomm AI Engine Direct - Enable per channel linear op #2822

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.

Sign up for GitHub

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

Jump to bottom
Closed
wants to merge 1 commit into from
Closed

Qualcomm AI Engine Direct - Enable per channel linear op #2822

wants to merge 1 commit into from

Conversation

chunit-quic
Copy link
Collaborator

  • Add per channel weight quantization for linear op
  • Bias quantization for per channel weight Linear op is not support yet

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Apr 3, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2822

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

✅ No Failures

As of commit 2efac57 with merge base 9fd1a0e (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 Apr 3, 2024
@chunit-quic chunit-quic changed the title [Qualcomm AI Engine Direct - Enable per channel linear op] Qualcomm AI Engine Direct - Enable per channel linear op Apr 3, 2024
@facebook-github-bot
Copy link
Contributor

@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@cccclai cccclai added the partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm label Apr 4, 2024
@cccclai
Copy link
Contributor

cccclai commented Apr 4, 2024

Hey thank you for submitting, do you mind rebasing? Seems like CI was broken and it's fixed in main branch now.

@chunit-quic @haowhsu-quic
[Qualcomm AI Engine Direct - Enable per channel linear op]
2efac57 
- Add per channel weight quantization for linear op
- Bias quantization for per channel weight Linear op is not support yet
@haowhsu-quic haowhsu-quic force-pushed the enable_per_channel_linear branch from e3c8e0c to 2efac57 Compare April 9, 2024 11:13
@haowhsu-quic
Copy link
Collaborator

Hi @cccclai , since @chunit-quic is on PTO, I help rebase this onto latest mainline.
This PR is important for incoming LLAMA enablement PR, could you kindly help merge this? thank you!

@facebook-github-bot
Copy link
Contributor

@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@facebook-github-bot
Copy link
Contributor

@cccclai merged this pull request in 554cd27.

@mergennachin mergennachin mentioned this pull request Apr 26, 2024
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@kirklandsign kirklandsign kirklandsign approved these changes

Assignees
No one assigned
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Merged partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@chunit-quic @facebook-github-bot @cccclai @haowhsu-quic @kirklandsign