Add dynamism support to aten.embedding and aten.split_with_sizes#6781
Merged
lsy323 merged 1 commit intopytorch:masterfrom Mar 20, 2024
Merged
Add dynamism support to aten.embedding and aten.split_with_sizes#6781lsy323 merged 1 commit intopytorch:masterfrom
aten.embedding and aten.split_with_sizes#6781lsy323 merged 1 commit intopytorch:masterfrom
Conversation
qihqi
approved these changes
Mar 20, 2024
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Support dynamism on
aten.embeddingandaten.split_with_sizesThe indices tensors to
aten.embeddingcan have more than 1 dimension. During tracing, it will be flattened. To avoid the view op with symbolic output shape, we flatten the indices tensor at FX level and the view with symbolic output shape will be handled byaten.view->xla.dynamic_viewpass.Add an FX pass to decompose
aten.split_with_sizesinto slice ops to reuse the dynamism added to slice.Test: