remove unused tensors from VK model's graph #4427
Closed
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/4427
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit c09fe87 with merge base 889e5cb ( 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: D60257047 |
SS-JIA
approved these changes
Jul 25, 2024
copyrightly
added a commit
to copyrightly/executorch
that referenced
this pull request
Jul 25, 2024
Summary: Pull Request resolved: pytorch#4427 We implemented [operators fusion](pytorch#3769) (`conv+bn`) which fused `conv` and `bn`'s weights and biases, but the old parameters are not deleted. Hence we saw that VK model's size is nearly twice large as CPU's. As regards mobilenet_v2, before this diff CPU vs VK: 14M vs 22M. After this diff, both of them have 14M. Reviewed By: SS-JIA Differential Revision: D60257047
copyrightly
force-pushed
the
export-D60257047
branch
from
c5d02e3
to
9a5455d
Compare
|
This pull request was exported from Phabricator. Differential Revision: D60257047 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D60257047 |
copyrightly
added a commit
to copyrightly/executorch
that referenced
this pull request
Jul 25, 2024
Summary: Pull Request resolved: pytorch#4427 We implemented [operators fusion](pytorch#3769) (`conv+bn`) which fused `conv` and `bn`'s weights and biases, but the old parameters are not deleted. Hence we saw that VK model's size is nearly twice large as CPU's. As regards mobilenet_v2, before this diff CPU vs VK: 14M vs 22M. After this diff, both of them have 14M. Reviewed By: SS-JIA Differential Revision: D60257047
copyrightly
force-pushed
the
export-D60257047
branch
from
9a5455d
to
0855797
Compare
copyrightly
added a commit
to copyrightly/executorch
that referenced
this pull request
Jul 26, 2024
Summary: Pull Request resolved: pytorch#4427 We implemented [operators fusion](pytorch#3769) (`conv+bn`) which fused `conv` and `bn`'s weights and biases, but the old parameters are not deleted. Hence we saw that VK model's size is nearly twice large as CPU's. As regards mobilenet_v2, before this diff CPU vs VK: 14M vs 22M. After this diff, both of them have 14M. Reviewed By: SS-JIA Differential Revision: D60257047
copyrightly
force-pushed
the
export-D60257047
branch
from
0855797
to
ca060d6
Compare
|
This pull request was exported from Phabricator. Differential Revision: D60257047 |
Summary: Pull Request resolved: pytorch#4427 We implemented [operators fusion](pytorch#3769) (`conv+bn`) which fused `conv` and `bn`'s weights and biases, but the old parameters are not deleted. Hence we saw that VK model's size is nearly twice large as CPU's. As regards mobilenet_v2, before this diff CPU vs VK: 14M vs 22M. After this diff, both of them have 14M. Reviewed By: SS-JIA Differential Revision: D60257047
copyrightly
force-pushed
the
export-D60257047
branch
from
ca060d6
to
c09fe87
Compare
|
This pull request was exported from Phabricator. Differential Revision: D60257047 |
|
This pull request has been merged in faeeca8. |
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:
We implemented operators fusion (
conv+bn) which fusedconvandbn's weights and biases, but the old parameters are not deleted. Hence we saw that VK model's size is nearly twice large as CPU's.As regards mobilenet_v2, before this diff CPU vs VK: 14M vs 22M. After this diff, both of them have 14M.
Differential Revision: D60257047