Add inplace quantizer examples #2345
Merged
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/ao/2345
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 62483bc with merge base 7e7ea92 ( 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: D76312488 |
|
This pull request was exported from Phabricator. Differential Revision: D76312488 |
cccclai
force-pushed
the
export-D76312488
branch
from
2779ddb to
6e1edbb
Compare
cccclai
added a commit
to cccclai/ao
that referenced
this pull request
Jun 16, 2025
Summary: Pull Request resolved: pytorch#2345 Add a quantizer example for in place ops Rollback Plan: Differential Revision: D76312488
|
This pull request was exported from Phabricator. Differential Revision: D76312488 |
cccclai
force-pushed
the
export-D76312488
branch
from
6e1edbb to
1a54331
Compare
cccclai
added a commit
to cccclai/ao
that referenced
this pull request
Jun 16, 2025
Summary: Pull Request resolved: pytorch#2345 Add a quantizer example for in place ops Rollback Plan: Differential Revision: D76312488
|
This pull request was exported from Phabricator. Differential Revision: D76312488 |
cccclai
force-pushed
the
export-D76312488
branch
from
1a54331 to
52dbbc6
Compare
cccclai
added a commit
to cccclai/ao
that referenced
this pull request
Jun 17, 2025
Summary: Pull Request resolved: pytorch#2345 Add a quantizer example for in place ops, and add a patch to the constant fold pass such that the mutable buffer won't be folded Differential Revision: D76312488
jerryzh168
reviewed
Jun 17, 2025
| # Identify mutable buffers by finding copy_ operations | ||
| self.mutable_buffers = self._find_mutable_buffers() | ||
|
|
||
| def _find_mutable_buffers(self) -> set[torch.fx.Node]: |
There was a problem hiding this comment.
why is this change needed? is there a test that exercises this code path?
There was a problem hiding this comment.
Yeah, the added test will fail if we have this code path. The quantize_per_tensor_default will be folded together with the mutable buffer, which is not what we want
|
This pull request was exported from Phabricator. Differential Revision: D76312488 |
cccclai
added a commit
to cccclai/ao
that referenced
this pull request
Jun 17, 2025
Summary: Pull Request resolved: pytorch#2345 Add a quantizer example for in place ops, and add a patch to the constant fold pass such that the mutable buffer won't be folded Reviewed By: jerryzh168 Differential Revision: D76312488
cccclai
force-pushed
the
export-D76312488
branch
from
52dbbc6 to
7c1133d
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76312488 |
cccclai
added a commit
to cccclai/ao
that referenced
this pull request
Jun 17, 2025
Summary: Pull Request resolved: pytorch#2345 Add a quantizer example for in place ops, and add a patch to the constant fold pass such that the mutable buffer won't be folded Reviewed By: jerryzh168 Differential Revision: D76312488
cccclai
force-pushed
the
export-D76312488
branch
from
7c1133d to
83395a6
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76312488 |
cccclai
added a commit
to cccclai/ao
that referenced
this pull request
Jun 17, 2025
Summary: Pull Request resolved: pytorch#2345 Add a quantizer example for in place ops, and add a patch to the constant fold pass such that the mutable buffer won't be folded Reviewed By: jerryzh168 Differential Revision: D76312488
cccclai
force-pushed
the
export-D76312488
branch
from
83395a6 to
e4e84dd
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76312488 |
cccclai
added a commit
to cccclai/ao
that referenced
this pull request
Jun 17, 2025
Summary: Pull Request resolved: pytorch#2345 Add a quantizer example for in place ops, and add a patch to the constant fold pass such that the mutable buffer won't be folded Reviewed By: jerryzh168 Differential Revision: D76312488
cccclai
force-pushed
the
export-D76312488
branch
from
e4e84dd to
f67507c
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76312488 |
cccclai
added a commit
to cccclai/ao
that referenced
this pull request
Jun 17, 2025
Summary: Pull Request resolved: pytorch#2345 Add a quantizer example for in place ops, and add a patch to the constant fold pass such that the mutable buffer won't be folded Reviewed By: jerryzh168 Differential Revision: D76312488
cccclai
force-pushed
the
export-D76312488
branch
from
f67507c to
0498b7d
Compare
pytorch-bot bot
pushed a commit
to pytorch/pytorch
that referenced
this pull request
Jun 17, 2025
Summary: Similar to pytorch/ao#2345 During constant folding, we shouldn't fold the mutable buffers. In the pass, we will find out the mutable buffer first, and then skip them during folding Test Plan: The added unit test test_constant_folding_mutable_buffer Rollback Plan: Differential Revision: D76844103
|
This pull request was exported from Phabricator. Differential Revision: D76312488 |
cccclai
added a commit
to cccclai/ao
that referenced
this pull request
Jun 17, 2025
Summary: Pull Request resolved: pytorch#2345 Add a quantizer example for in place ops, and add a patch to the constant fold pass such that the mutable buffer won't be folded Reviewed By: jerryzh168 Differential Revision: D76312488
cccclai
force-pushed
the
export-D76312488
branch
from
0498b7d to
5f38f5c
Compare
jerryzh168
added
the
topic: improvement
Summary: Pull Request resolved: pytorch#2345 Add a quantizer example for in place ops, and add a patch to the constant fold pass such that the mutable buffer won't be folded Reviewed By: jerryzh168 Differential Revision: D76312488
|
This pull request was exported from Phabricator. Differential Revision: D76312488 |
cccclai
force-pushed
the
export-D76312488
branch
from
5f38f5c to
62483bc
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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:
Add a quantizer example for in place ops
Rollback Plan:
Differential Revision: D76312488