Move initializers from subgraph to the main graph to reduce memory #12310
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
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Outdated suggestions cannot be applied.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.
Description:
Gpt2 beam search model uses 2.5x memory (For example, 0.6G model uses 1.5G memory). The cause is initializers kept in subgraph uses more memory in Model creation and resolving graph in ORT (It looks like a bug that duplicates initializers). Here we use a walkaround to move initializers from subgraph to main graph.
T5 cannot apply similar walkaround since ORT will fail. The cause need investigation so this PR only applies to gpt2.
Motivation and Context
#12246