Skip to content

Qualcomm AI Engine Direct - Add block quantization to llama #10225

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

Merged
merged 1 commit into from
Apr 16, 2025

Conversation

chunit-quic
Copy link
Collaborator

  • Add CLI argument to use block quantization for llama

@chunit-quic chunit-quic requested a review from cccclai as a code owner April 16, 2025 06:29
Copy link

pytorch-bot bot commented Apr 16, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10225

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

❌ 1 New Failure

As of commit 5b3d1ec with merge base 4559a61 (image):

NEW FAILURE - The following job has failed:

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 16, 2025
@chunit-quic
Copy link
Collaborator Author

Hi @cccclai,

It's a straightforward PR. The goal is to add an argument to support LPBQ (Low Power Block Quantization) for LLaMA. Thank you!

- Add CLI argument to use block quantization for llama
@chunit-quic chunit-quic force-pushed the add_llama_block_quant branch from 8da6241 to 5b3d1ec Compare April 16, 2025 07:09
@cccclai
Copy link
Contributor

cccclai commented Apr 16, 2025

Oh wow, this is awesome. Any chance you have data point on this?

@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 release notes: qualcomm Changes to the Qualcomm backend delegate label Apr 16, 2025
Copy link
Contributor

@cccclai cccclai left a comment

Choose a reason for hiding this comment

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

Thanks!

@cccclai cccclai merged commit e6c7b30 into pytorch:main Apr 16, 2025
89 of 90 checks passed
keyprocedure pushed a commit to keyprocedure/executorch that referenced this pull request Apr 21, 2025
…10225)

- Add CLI argument to use block quantization for llama

Co-authored-by: Chun-I Tsai <chunit@qti.qualcomm.com>
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. release notes: qualcomm Changes to the Qualcomm backend delegate
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants