-
Notifications
You must be signed in to change notification settings - Fork 684
Refactor quantizer: Only replace with per-tensor variants #14974
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
base: main
Are you sure you want to change the base?
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14974
Note: Links to docs will display an error until the docs builds have been completed. ❌ 7 New Failures, 3 Pending, 2 Unrelated FailuresAs of commit f84f831 with merge base 3591604 ( NEW FAILURES - The following jobs have failed:
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. |
This PR needs a
|
c434d1e
to
3e65bea
Compare
) Summary: In our previous flow, we would replace ops with default variants, have a special fusion pass which constructs singleton tensors for a variety of fused quantized ops, and then we would call a replace ops to turn them into per-tensor-variants. I confirmed this was for legacy reasons, so a cleanup was much due. This diff also fixes any ref implementations during the refactor. Reviewed By: zonglinpeng Differential Revision: D83873738
3e65bea
to
33a47e1
Compare
) Summary: In our previous flow, we would replace ops with default variants, have a special fusion pass which constructs singleton tensors for a variety of fused quantized ops, and then we would call a replace ops to turn them into per-tensor-variants. I confirmed this was for legacy reasons, so a cleanup was much due. This diff also fixes any ref implementations during the refactor. Reviewed By: zonglinpeng Differential Revision: D83873738
33a47e1
to
43e31be
Compare
) Summary: In our previous flow, we would replace ops with default variants, have a special fusion pass which constructs singleton tensors for a variety of fused quantized ops, and then we would call a replace ops to turn them into per-tensor-variants. I confirmed this was for legacy reasons, so a cleanup was much due. This diff also fixes any ref implementations during the refactor. Reviewed By: zonglinpeng Differential Revision: D83873738
Summary: Matmul was relying on linear infra which didn't support batched second argument. This adds support. Differential Revision: D84279595
) Summary: In our previous flow, we would replace ops with default variants, have a special fusion pass which constructs singleton tensors for a variety of fused quantized ops, and then we would call a replace ops to turn them into per-tensor-variants. I confirmed this was for legacy reasons, so a cleanup was much due. This diff also fixes any ref implementations during the refactor. Reviewed By: zonglinpeng Differential Revision: D83873738
43e31be
to
f84f831
Compare
Summary:
In our previous flow, we would replace ops with default variants, have a special fusion pass which constructs singleton tensors for a variety of fused quantized ops, and then we would call a replace ops to turn them into per-tensor-variants.
I confirmed this was for legacy reasons, so a cleanup was much due.
This diff also fixes any ref implementations during the refactor.
Reviewed By: zonglinpeng
Differential Revision: D83873738