Python: Fix Onnx Connector Memory Problem with Onnx #9716
+12
−18
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
Onnx currently faces memory issues when dividing functionality among multiple methods
markwallace-microsoft
added
the
python
github-actions
bot
changed the title
Python Unit Test Overview
|
nmoeller
changed the title
moonbox3
approved these changes
Nov 15, 2024
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Outdated suggestions cannot be applied.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.
Onnx currently faces memory issues when dividing functionality among multiple methods
Motivation and Context
I was experiencing weird non reproducible memory issues with connector when using phi-3 vision, after tracing the memory it turn out there are some issues when Parameters & Generation are not in the same function. I am already in contact with the PG to adress the issue also in onnx.
There seems to be a memory on the c level with pybind, because the parameters show an non deterministc behavior, but they should determistic.
To fix the current problem i've decided to merge the Parameter Method and the Generation Method.
Description
Contribution Checklist