Introduce apply_torch_ops_aten_passes to test mul fusion e2e #11741
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11741
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 Cancelled Job, 2 Unrelated FailuresAs of commit 38c5b5b with merge base bf4acb3 ( CANCELLED JOB - The following job was cancelled. Please retry:
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
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
force-pushed
the
export-D76469613
branch
from
49e1e96 to
d86f728
Compare
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jun 16, 2025
…#11741) Summary: Pull Request resolved: pytorch#11741 This diff 1) extends export_to_edge() with apply_prelowering_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jun 16, 2025
…#11741) Summary: Pull Request resolved: pytorch#11741 This diff 1) extends export_to_edge() with apply_prelowering_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
eigen-k
force-pushed
the
export-D76469613
branch
from
d86f728 to
1903db9
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jun 16, 2025
…#11741) Summary: Pull Request resolved: pytorch#11741 This diff 1) extends export_to_edge() with apply_prelowering_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
eigen-k
force-pushed
the
export-D76469613
branch
from
1903db9 to
ba3a5a9
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
force-pushed
the
export-D76469613
branch
from
ba3a5a9 to
ccc998e
Compare
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jun 17, 2025
…#11741) Summary: Pull Request resolved: pytorch#11741 This diff 1) extends export_to_edge() with apply_prelowering_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jun 17, 2025
Summary: Pull Request resolved: pytorch#11741 This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
eigen-k
force-pushed
the
export-D76469613
branch
from
ccc998e to
15873c3
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
force-pushed
the
export-D76469613
branch
from
15873c3 to
2efa68a
Compare
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 3, 2025
Summary: This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 3, 2025
Summary: This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 8, 2025
Summary: This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 8, 2025
Summary: Pull Request resolved: pytorch#11741 This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 8, 2025
Summary: This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 8, 2025
Summary: Pull Request resolved: pytorch#11741 This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
eigen-k
force-pushed
the
export-D76469613
branch
2 times, most recently
from
853e63a to
c0175e7
Compare
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 9, 2025
Summary: This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 9, 2025
Summary: This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 9, 2025
Summary: Pull Request resolved: pytorch#11741 This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 9, 2025
Summary: This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
hsharma35
approved these changes
Jul 9, 2025
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 9, 2025
Summary: This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
eigen-k
added a commit
to eigen-k/executorch
that referenced
this pull request
Jul 9, 2025
Summary: This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
Summary: This diff 1) extends export_to_edge() with apply_torch_ops_passes() call We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge() 2) implements e2e mul fusion test. We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely. Reviewed By: hsharma35 Differential Revision: D76469613
|
This pull request was exported from Phabricator. Differential Revision: D76469613 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
This diff
We need this to grab the actual mul argument value and fusing in later passes. Otherwise, the constant gets lifted by _lower_ep_to_edge()
We test that both ReplaceMulTensorWithMulAndFullOpsPass() and FuseMulTensorIntoQuantPass() passes get applied correctly and which results into mul.Tensor being removed completely.
Reviewed By: hsharma35
Differential Revision: D76469613