[CoreML Backend] Optimize memory when exporting. #2341
Closed
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Outdated suggestions cannot be applied.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.
CoreML delegate when converting the
mlpackage
to an in-memory representation reads the directory contents in themlpackage
directory and writes it to a memory buffer this is expensive and the copying is not required.The change in the PR addresses by memory mapping the file contents to fixed addresses in the allocated memory, no memory is dirtied and the OS will bring the pages only when the bytes are read.