Skip to content

Claen up op interface #1998

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 1, 2025
Merged

Conversation

metascroy
Copy link
Contributor

Summary:
This PR adds mr based kernel selection, and cleans up the op interface.

  1. Removes linear.h and uses the new channelwise_8bit_activation_groupwise_lowbit_weight.h we created in an earlier diff
  2. Uses packed_weights_offset functions from ukernel, rather than manually computing the offset
  3. Removes the compute policies (parallalel_mc_parallel_nc, single_mc_parallel_nc). Only one of these policies is needed, and having both complicated adding mr based kernel selection.
  4. Moves UkernelConfig into its own file kernel_config.h from kernel_selection.h.
  5. Adds mr-based kernel selection (select mr ukernel based on m). This is in prepearation for KleidiAI GEMM kernel selection (next diff).

Reviewed By: Jack-Khuu

Differential Revision: D72179480

Summary:
This PR adds mr based kernel selection, and cleans up the op interface.

1. Removes linear.h and uses the new channelwise_8bit_activation_groupwise_lowbit_weight.h we created in an earlier diff
2. Uses packed_weights_offset functions from ukernel, rather than manually computing the offset
3. Removes the compute policies (parallalel_mc_parallel_nc, single_mc_parallel_nc).  Only one of these policies is needed, and having both complicated adding mr based kernel selection.
4. Moves UkernelConfig into its own file kernel_config.h from kernel_selection.h.
4. Adds mr-based kernel selection (select mr ukernel based on m).  This is in prepearation for KleidiAI GEMM kernel selection (next diff).

Reviewed By: Jack-Khuu

Differential Revision: D72179480
Copy link

pytorch-bot bot commented Apr 1, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1998

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

❌ 1 New Failure

As of commit 43f7dbf with merge base 5e4d50c (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 1, 2025
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D72179480

@facebook-github-bot facebook-github-bot merged commit c9b1490 into pytorch:main Apr 1, 2025
17 of 22 checks passed
jainapurva pushed a commit that referenced this pull request Apr 8, 2025
Differential Revision: D72179480

Pull Request resolved: #1998
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. fb-exported
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants