[ExecuTorch][Weight Sharing][XNNPACK] Serialize constant tensors into named data map #9153
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
… named data map We serialize tensors into the named data map, and return the output in preprocess result. Allowing for XNNPACK to share tensors with the same name (instead of duplicating). A key change here is with fused tensors. For BN and Convolution Fusion, we fuse the conv weights and bias with the BN parameters creating new tensors. We then create get_attr nodes for these new parameters. Due to the graph.fx interpreter in export pass base, the new names we create for these new tensors are lost each time. As a result, at the end we introduce a new pass to preserve the names we created. This seems a little hacky for now, but is the only way to preserve the new fused names. Differential Revision: [D70315207](https://our.internmc.facebook.com/intern/diff/D70315207/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D70315207/)! [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9153
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 395733d with merge base 630d0cc ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Mar 11, 2025
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D70315207 |
…ensors into named data map" We serialize tensors into the named data map, and return the output in preprocess result. Allowing for XNNPACK to share tensors with the same name (instead of duplicating). A key change here is with fused tensors. For BN and Convolution Fusion, we fuse the conv weights and bias with the BN parameters creating new tensors. We then create get_attr nodes for these new parameters. Due to the graph.fx interpreter in export pass base, the new names we create for these new tensors are lost each time. As a result, at the end we introduce a new pass to preserve the names we created. This seems a little hacky for now, but is the only way to preserve the new fused names. Differential Revision: [D70315207](https://our.internmc.facebook.com/intern/diff/D70315207/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D70315207/)! [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D70315207 |
…ensors into named data map" We serialize tensors into the named data map, and return the output in preprocess result. Allowing for XNNPACK to share tensors with the same name (instead of duplicating). A key change here is with fused tensors. For BN and Convolution Fusion, we fuse the conv weights and bias with the BN parameters creating new tensors. We then create get_attr nodes for these new parameters. Due to the graph.fx interpreter in export pass base, the new names we create for these new tensors are lost each time. As a result, at the end we introduce a new pass to preserve the names we created. This seems a little hacky for now, but is the only way to preserve the new fused names. Differential Revision: [D70315207](https://our.internmc.facebook.com/intern/diff/D70315207/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D70315207/)! [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D70315207 |
kirklandsign
approved these changes
Mar 13, 2025
…ensors into named data map" We serialize tensors into the named data map, and return the output in preprocess result. Allowing for XNNPACK to share tensors with the same name (instead of duplicating). A key change here is with fused tensors. For BN and Convolution Fusion, we fuse the conv weights and bias with the BN parameters creating new tensors. We then create get_attr nodes for these new parameters. Due to the graph.fx interpreter in export pass base, the new names we create for these new tensors are lost each time. As a result, at the end we introduce a new pass to preserve the names we created. This seems a little hacky for now, but is the only way to preserve the new fused names. Differential Revision: [D70315207](https://our.internmc.facebook.com/intern/diff/D70315207/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D70315207/)! [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D70315207 |
…ensors into named data map" We serialize tensors into the named data map, and return the output in preprocess result. Allowing for XNNPACK to share tensors with the same name (instead of duplicating). A key change here is with fused tensors. For BN and Convolution Fusion, we fuse the conv weights and bias with the BN parameters creating new tensors. We then create get_attr nodes for these new parameters. Due to the graph.fx interpreter in export pass base, the new names we create for these new tensors are lost each time. As a result, at the end we introduce a new pass to preserve the names we created. This seems a little hacky for now, but is the only way to preserve the new fused names. Differential Revision: [D70315207](https://our.internmc.facebook.com/intern/diff/D70315207/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D70315207/)! [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D70315207 |
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
SS-JIA
pushed a commit
that referenced
this pull request
Mar 15, 2025
… named data map (#9295) This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #9153 by @mcr229 ^ Please use this as the source of truth for the PR details, comments, and reviews ghstack PR base: https://github.com/pytorch/executorch/tree/gh/mcr229/9/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/mcr229/9/head Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/mcr229/8/orig Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/mcr229/9/orig @diff-train-skip-merge Co-authored-by: Max Ren <[email protected]>
SS-JIA
pushed a commit
that referenced
this pull request
Mar 15, 2025
… named data map Pull Request resolved: #9153 We serialize tensors into the named data map, and return the output in preprocess result. Allowing for XNNPACK to share tensors with the same name (instead of duplicating). A key change here is with fused tensors. For BN and Convolution Fusion, we fuse the conv weights and bias with the BN parameters creating new tensors. We then create get_attr nodes for these new parameters. Due to the graph.fx interpreter in export pass base, the new names we create for these new tensors are lost each time. As a result, at the end we introduce a new pass to preserve the names we created. This seems a little hacky for now, but is the only way to preserve the new fused names. Differential Revision: [D70315207](https://our.internmc.facebook.com/intern/diff/D70315207/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D70315207/)! ghstack-source-id: 271732046
|
@pytorchbot cherry-pick --onto main -c "repair wrong merge order" |
|
❌ 🤖 pytorchbot command failed: Try |
|
@pytorchbot cherry-pick --onto main -c "release" |
Cherry picking #9153Command Details for Dev Infra teamRaised by workflow job |
facebook-github-bot
had a problem deploying
to
cherry-pick-bot
GitHub Actions
Failure
|
For context, I messed up the merging order of the bot generated PR, I accidentally started merging from this PR and then later noticed that the one below it hadn't been merged yet. After I merged the one below this, I thought that the changes from this PR onward didn't make it into cc: @kirklandsign @mcr229 |
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.
Stack from ghstack (oldest at bottom):
We serialize tensors into the named data map, and return the output in preprocess result. Allowing for XNNPACK to share tensors with the same name (instead of duplicating).
A key change here is with fused tensors. For BN and Convolution Fusion, we fuse the conv weights and bias with the BN parameters creating new tensors. We then create get_attr nodes for these new parameters. Due to the graph.fx interpreter in export pass base, the new names we create for these new tensors are lost each time. As a result, at the end we introduce a new pass to preserve the names we created. This seems a little hacky for now, but is the only way to preserve the new fused names.
Differential Revision: D70315207
NOTE FOR REVIEWERS: This PR has internal Meta-specific changes or comments, please review them on Phabricator!