Skip to content

Add quantization and partitioner flow in the qualcomm doc #12387

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
Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add quantization and partitioner flow in the qualcomm doc #12387

wants to merge 1 commit into from
+134 −13

Conversation

cccclai
Copy link
Contributor

@cccclai cccclai commented Jul 11, 2025

Summary: Add a session to describe how to lower a model to HTP, including quantization step.

Differential Revision: D78117959

@cccclai cccclai requested a review from mergennachin as a code owner July 11, 2025 04:54
@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Jul 11, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12387

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

✅ You can merge normally! (4 Unrelated Failures)

As of commit 1263030 with merge base 9591978 (image):

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

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 Jul 11, 2025
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D78117959

@github-actions GitHub Actions
Copy link

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

@cccclai cccclai mentioned this pull request Jul 11, 2025
Open
DannyYuyang-quic
DannyYuyang-quic reviewed Jul 11, 2025
View reviewed changes
shewu-quic
shewu-quic approved these changes Jul 11, 2025
View reviewed changes
Copy link
Collaborator

@shewu-quic shewu-quic left a comment

Choose a reason for hiding this comment

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

Thank you for the effort to make document better!!

cccclai added a commit to cccclai/executorch-1 that referenced this pull request Jul 11, 2025
@cccclai @facebook-github-bot
Add quantization and partitioner flow in the qualcomm doc (pytorch#12387
2384c7d 
)

Summary:

Add a session to describe how to lower a model to HTP, including quantization step.

Differential Revision: D78117959
@cccclai cccclai force-pushed the export-D78117959 branch from 33ad9d8 to 2384c7d Compare July 11, 2025 16:57
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D78117959

cccclai added a commit to cccclai/executorch-1 that referenced this pull request Jul 11, 2025
@cccclai @facebook-github-bot
Add quantization and partitioner flow in the qualcomm doc (pytorch#12387
aafb8af 
)

Summary:

Add a session to describe how to lower a model to HTP, including quantization step.

Differential Revision: D78117959
@cccclai cccclai force-pushed the export-D78117959 branch from 2384c7d to aafb8af Compare July 11, 2025 17:03
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D78117959

@cccclai
Copy link
Contributor Author

cccclai commented Jul 11, 2025

Hi @metascroy, this PR is for Qualcomm doc and it includes quantization.

cccclai added a commit to cccclai/executorch-1 that referenced this pull request Jul 11, 2025
@cccclai @facebook-github-bot
Add quantization and partitioner flow in the qualcomm doc (pytorch#12387
e94a9e1 
)

Summary:

Add a session to describe how to lower a model to HTP, including quantization step.

Differential Revision: D78117959
@cccclai cccclai force-pushed the export-D78117959 branch from aafb8af to e94a9e1 Compare July 11, 2025 18:50
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D78117959

cccclai added a commit to cccclai/executorch-1 that referenced this pull request Jul 11, 2025
@cccclai @facebook-github-bot
Add quantization and partitioner flow in the qualcomm doc (pytorch#12387
5a3a437 
)

Summary:
Pull Request resolved: pytorch#12387

Add a session to describe how to lower a model to HTP, including quantization step.

Differential Revision: D78117959
@cccclai cccclai force-pushed the export-D78117959 branch from e94a9e1 to 5a3a437 Compare July 11, 2025 18:55
cccclai added a commit to cccclai/executorch-1 that referenced this pull request Jul 11, 2025
@cccclai @facebook-github-bot
Add quantization and partitioner flow in the qualcomm doc (pytorch#12387
111d159 
)

Summary:

Add a session to describe how to lower a model to HTP, including quantization step.

Differential Revision: D78117959
@cccclai cccclai force-pushed the export-D78117959 branch from 5a3a437 to 111d159 Compare July 11, 2025 22:14
@cccclai @facebook-github-bot
Add quantization and partitioner flow in the qualcomm doc (pytorch#12387
1263030 
)

Summary:
Pull Request resolved: pytorch#12387

Add a session to describe how to lower a model to HTP, including quantization step.

Differential Revision: D78117959
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D78117959

@cccclai cccclai force-pushed the export-D78117959 branch from 111d159 to 1263030 Compare July 11, 2025 22:19
metascroy
metascroy reviewed Jul 14, 2025
View reviewed changes
docs/source/backends-qualcomm.md
#### Step 2: [Optional] Quantize Your Model
Choose between quantization approaches, post training quantization (PTQ) or quantization aware training (QAT):
```python
from executorch.backends.qualcomm.quantizer.quantizer import QnnQuantizer
Copy link
Contributor

Choose a reason for hiding this comment

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

Is QnnQuantizer configurable? If so, can we document the configuration?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@metascroy metascroy metascroy left review comments

@DannyYuyang-quic DannyYuyang-quic DannyYuyang-quic left review comments

@shewu-quic shewu-quic shewu-quic approved these changes

@mergennachin mergennachin Awaiting requested review from mergennachin mergennachin is a code owner

@haowhsu-quic haowhsu-quic Awaiting requested review from haowhsu-quic

@winskuo-quic winskuo-quic Awaiting requested review from winskuo-quic

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. fb-exported
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@cccclai @facebook-github-bot @shewu-quic @metascroy @DannyYuyang-quic