Skip fuse_mm_elementwise fusion with model output in the middle #1000
+50
−17
Conversation
This file contains 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
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D56340320 |
aakhundov
added a commit
to aakhundov/AITemplate-1
that referenced
this pull request
Apr 19, 2024
…bookincubator#1000) Summary: `fuse_mm_elementwise` transformation fuses linear patterns into single ops. As a result, all intermediate outputs in the pattern are eliminated. In a special case when one or more of those intermediate outputs are model outputs, this leads to those model outputs vanishing after the fusion. Here we add skipping the fusion when one of the intermediate outputs in the detected pattern is a model output. Differential Revision: D56340320
aakhundov
added a commit
to aakhundov/AITemplate-1
that referenced
this pull request
Apr 19, 2024
…bookincubator#1000) Summary: `fuse_mm_elementwise` transformation fuses linear patterns into single ops. As a result, all intermediate outputs in the pattern are eliminated. In a special case when one or more of those intermediate outputs are model outputs, this leads to those model outputs vanishing after the fusion. Here we add skipping the fusion when one of the intermediate outputs in the detected pattern is a model output. Differential Revision: D56340320
aakhundov
added a commit
to aakhundov/AITemplate-1
that referenced
this pull request
Apr 19, 2024
…bookincubator#1000) Summary: `fuse_mm_elementwise` transformation fuses linear patterns into single ops. As a result, all intermediate outputs in the pattern are eliminated. In a special case when one or more of those intermediate outputs are model outputs, this leads to those model outputs vanishing after the fusion. Here we add skipping the fusion when one of the intermediate outputs in the detected pattern is a model output. Reviewed By: mengyingdu Differential Revision: D56340320
aakhundov
force-pushed
the
export-D56340320
branch
from
3a27561
to
8583c7d
Compare
|
This pull request was exported from Phabricator. Differential Revision: D56340320 |
aakhundov
added a commit
to aakhundov/AITemplate-1
that referenced
this pull request
Apr 19, 2024
…bookincubator#1000) Summary: `fuse_mm_elementwise` transformation fuses linear patterns into single ops. As a result, all intermediate outputs in the pattern are eliminated. In a special case when one or more of those intermediate outputs are model outputs, this leads to those model outputs vanishing after the fusion. Here we add skipping the fusion when one of the intermediate outputs in the detected pattern is a model output. Reviewed By: mengyingdu Differential Revision: D56340320
aakhundov
force-pushed
the
export-D56340320
branch
from
8583c7d
to
bea39a8
Compare
|
This pull request was exported from Phabricator. Differential Revision: D56340320 |
…bookincubator#1000) Summary: `fuse_mm_elementwise` transformation fuses linear patterns into single ops. As a result, all intermediate outputs in the pattern are eliminated. In a special case when one or more of those intermediate outputs are model outputs, this leads to those model outputs vanishing after the fusion. Here we add skipping the fusion when one of the intermediate outputs in the detected pattern is a model output. Reviewed By: mengyingdu Differential Revision: D56340320
aakhundov
force-pushed
the
export-D56340320
branch
from
bea39a8
to
7b7ce77
Compare
|
This pull request was exported from Phabricator. Differential Revision: D56340320 |
|
This pull request has been merged in eb89bf6. |
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:
fuse_mm_elementwisetransformation fuses linear patterns into single ops. As a result, all intermediate outputs in the pattern are eliminated. In a special case when one or more of those intermediate outputs are model outputs, this leads to those model outputs vanishing after the fusion. Here we add skipping the fusion when one of the intermediate outputs in the detected pattern is a model output.Differential Revision: D56340320