Fix issue that the generated context cache model inputs/outputs order is not guaranteed #19195
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
HectorSVC
requested review from
skottmckay,
yuslepukhin,
adrianlizarraga,
jywu-msft and
chilo-ms
jywu-msft
reviewed
Jan 18, 2024
|
is it possible to add simple model test case which checks input/output order is preserved? |
yuslepukhin
reviewed
Jan 18, 2024
yuslepukhin
reviewed
Jan 18, 2024
yuslepukhin
reviewed
Jan 18, 2024
change the way to check whether file exist already since std::filesystem not available for some OS version
Yes. Figured out the trick of the model finally. |
jywu-msft
approved these changes
Jan 19, 2024
YUNQIUGUO
pushed a commit
that referenced
this pull request
Jan 23, 2024
… is not guaranteed (#19195) Fix issue that the generated context cache model inputs/outputs order is not guaranteed ### Description Currently, QNN EP generate the context cache model in Compile() method which only get access to the partitioned graph. And the inputs/outputs order for the partitioned graph is not guaranteed. And EP doesn't have the view of the input user model. Have to move the context cache model generation to a higher level in GraphPartitioner which has the view of the partitioned model. This is also a break down of PR for multi-partition support. #18865
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Outdated suggestions cannot be applied.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.
Fix issue that the generated context cache model inputs/outputs order is not guaranteed
Description
Currently, QNN EP generate the context cache model in Compile() method which only get access to the partitioned graph. And the inputs/outputs order for the partitioned graph is not guaranteed. And EP doesn't have a view of the input user model.
Have to move the context cache model generation to a higher level in GraphPartitioner which has the view of the partitioned model.
This is also a break down of PR #18865 for multi-partition support.