Precompute more metadata during plan #1938
Open
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
Collaborator
|
Wow, ok, this one may be more tricky than the new ops in onnx/ml :) |
threeseed
changed the title
Author
|
On further testing the symbol cache isn't going to be beneficial for most users so will leave it out. This is just the precompute piece. |
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Outdated suggestions cannot be applied.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.
For our use case we are executing basic ONNX models e.g. LinearClassifier millions of times.
And so the overhead of Tract is our biggest performance impact.
This PR aims to "front-load" more work during the plan stage.
Based on benchmarks we see a ~3x performance improvement.