XNNPACK: faster 4-bit packing #2649

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

digantdesai wants to merge 1 commit into pytorch:main from digantdesai:export-D55319010

Contributor

digantdesai commented Mar 25, 2024

Summary: Just use tensor methods, drop custom op and the previous python logic

Differential Revision: D55319010

pytorch-bot bot commented Mar 25, 2024 •

edited

Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2649

📄 Preview Python docs built from this PR

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

[PREEMPTIVE] - We recently implemented changes in pull job linux-jammy-py3.8-gcc11 / build

✅ No Failures

As of commit 2f8344d with merge base 853fb5b ():
💚 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 added CLA Signed fb-exported labels

Contributor

facebook-github-bot commented Mar 25, 2024

This pull request was exported from Phabricator. Differential Revision: D55319010

digantdesai added a commit to digantdesai/executorch-1 that referenced this pull request


          Better 4bit packing (pytorch#2649)

781ba31

Summary:

Just use tensor methods, drop custom op and the previous python logic

Differential Revision: D55319010

digantdesai force-pushed the export-D55319010 branch from c86cdfa to 781ba31 Compare

March 25, 2024 16:09

Contributor

facebook-github-bot commented Mar 25, 2024

This pull request was exported from Phabricator. Differential Revision: D55319010

digantdesai added a commit to digantdesai/executorch-1 that referenced this pull request


          Better 4bit packing (pytorch#2649)

a7a6221

Summary:

Just use tensor methods, drop custom op and the previous python logic

Differential Revision: D55319010

digantdesai force-pushed the export-D55319010 branch from 781ba31 to a7a6221 Compare

March 25, 2024 16:12

Contributor

facebook-github-bot commented Mar 25, 2024

This pull request was exported from Phabricator. Differential Revision: D55319010

digantdesai changed the title ~~Better 4bit packing~~ XNNPACK: faster 4bit packing

digantdesai changed the title ~~XNNPACK: faster 4bit packing~~ XNNPACK: faster 4-bit packing

digantdesai added a commit to digantdesai/executorch-1 that referenced this pull request


          Better 4bit packing (pytorch#2649)

f264904

Summary:

Just use tensor methods, drop custom op and the previous python logic

Differential Revision: D55319010

digantdesai force-pushed the export-D55319010 branch from a7a6221 to f264904 Compare

March 25, 2024 16:32

Contributor

facebook-github-bot commented Mar 25, 2024

This pull request was exported from Phabricator. Differential Revision: D55319010

digantdesai added a commit to digantdesai/executorch-1 that referenced this pull request


          Better 4bit packing (pytorch#2649)

13efb5c

Summary:

Just use tensor methods, drop custom op and the previous python logic

Differential Revision: D55319010

digantdesai force-pushed the export-D55319010 branch from f264904 to 13efb5c Compare

March 25, 2024 16:37

Contributor

facebook-github-bot commented Mar 25, 2024

This pull request was exported from Phabricator. Differential Revision: D55319010

digantdesai force-pushed the export-D55319010 branch from 13efb5c to 860df69 Compare

March 25, 2024 22:56

digantdesai added a commit to digantdesai/executorch-1 that referenced this pull request


          Better 4bit packing (pytorch#2649)

860df69

Summary:

Just use tensor methods, drop custom op and the previous python logic

Also drop aot_utils for xnnpack

Reviewed By: GregoryComer

Differential Revision: D55319010

Contributor

facebook-github-bot commented Mar 25, 2024

This pull request was exported from Phabricator. Differential Revision: D55319010

digantdesai added a commit to digantdesai/executorch-1 that referenced this pull request


          Better 4bit packing (pytorch#2649)

012e2cb

Summary:

Just use tensor methods, drop custom op and the previous python logic

Also drop aot_utils for xnnpack

Reviewed By: GregoryComer

Differential Revision: D55319010

digantdesai force-pushed the export-D55319010 branch from 860df69 to 012e2cb Compare

March 25, 2024 23:22

Contributor

facebook-github-bot commented Mar 25, 2024

This pull request was exported from Phabricator. Differential Revision: D55319010

digantdesai added a commit to digantdesai/executorch-1 that referenced this pull request


          Better 4bit packing (pytorch#2649)

53ba705

Summary:

Just use tensor methods, drop custom op and the previous python logic

Also drop aot_utils for xnnpack

Reviewed By: GregoryComer

Differential Revision: D55319010

digantdesai force-pushed the export-D55319010 branch from 012e2cb to 53ba705 Compare

March 25, 2024 23:47

Contributor

facebook-github-bot commented Mar 25, 2024

This pull request was exported from Phabricator. Differential Revision: D55319010

kimishpatel approved these changes

View reviewed changes

digantdesai mentioned this pull request

Refactor aot_util build #2631

Closed


          Better 4bit packing (pytorch#2649)

2f8344d

Summary:

Just use tensor methods, drop custom op and the previous python logic

Also drop aot_utils for xnnpack

Reviewed By: kimishpatel, GregoryComer

Differential Revision: D55319010

digantdesai force-pushed the export-D55319010 branch from 53ba705 to 17ca767 Compare

March 27, 2024 05:10

digantdesai added a commit to digantdesai/executorch-1 that referenced this pull request


          Better 4bit packing (pytorch#2649)

17ca767

Summary:

Just use tensor methods, drop custom op and the previous python logic

Also drop aot_utils for xnnpack

Reviewed By: kimishpatel, GregoryComer

Differential Revision: D55319010

Contributor

facebook-github-bot commented Mar 27, 2024

This pull request was exported from Phabricator. Differential Revision: D55319010

digantdesai force-pushed the export-D55319010 branch from 17ca767 to 2f8344d Compare

March 27, 2024 05:10

Contributor

facebook-github-bot commented Mar 27, 2024

This pull request was exported from Phabricator. Differential Revision: D55319010

facebook-github-bot closed this in

3c64e8f

facebook-github-bot added the Merged label

Contributor

facebook-github-bot commented Mar 27, 2024

This pull request has been merged in 3c64e8f.

Contributor Author

digantdesai commented Mar 27, 2024

@pytorchbot cherry-pick --onto release/0.2 -c critical

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

Labels

CLA Signed fb-exported Merged