Fix name of const tensors in const_prop_pass.py #7301
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/executorch/7301
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit c09bdb3 with merge base 3f7eb3b ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66568874 |
pssrawat
force-pushed
the
export-D66568874
branch
from
3ed2228 to
6c8813e
Compare
pssrawat
added a commit
to pssrawat/executorch
that referenced
this pull request
Dec 13, 2024
Summary: After XNNPack delegation, for llama predictor, some const tensors in the exported program are eliminated, e.g., c__prop_tensor_constant32 in P1688172607. If we run constant_prop_pass after this point, the const tensor naming logic in the implementation is incorrect, and could create redefinition of const tensors (error in P1687944413). This diff fixes the naming logic of const tensors in the pass. Differential Revision: D66568874
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66568874 |
pssrawat
force-pushed
the
export-D66568874
branch
from
6c8813e to
43afdd8
Compare
pssrawat
added a commit
to pssrawat/executorch
that referenced
this pull request
Dec 13, 2024
Summary: After XNNPack delegation, for llama predictor, some const tensors in the exported program are eliminated, e.g., c__prop_tensor_constant32 in P1688172607. If we run constant_prop_pass after this point, the const tensor naming logic in the implementation is incorrect, and could create redefinition of const tensors (error in P1687944413). This diff fixes the naming logic of const tensors in the pass. Differential Revision: D66568874
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66568874 |
Summary: After XNNPack delegation, for llama predictor, some const tensors in the exported program are eliminated, e.g., c__prop_tensor_constant32 in P1688172607. If we run constant_prop_pass after this point, the const tensor naming logic in the implementation is incorrect, and could create redefinition of const tensors (error in P1687944413). This diff fixes the naming logic of const tensors in the pass. Differential Revision: D66568874
pssrawat
force-pushed
the
export-D66568874
branch
from
43afdd8 to
c09bdb3
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D66568874 |
tarun292
approved these changes
Dec 16, 2024
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:
After XNNPack delegation, for llama predictor, some const tensors in the exported program are eliminated, e.g., c__prop_tensor_constant32 in P1688172607.
If we run constant_prop_pass after this point, the const tensor naming logic in the implementation is incorrect, and could create redefinition of const tensors (error in P1687944413).
This diff fixes the naming logic of const tensors in the pass.
Differential Revision: D66568874