[QNN-EP] Parallelize graph finalization#27629
Draft
quic-calvnguy wants to merge 1 commit intomicrosoft:mainfrom
Draft
[QNN-EP] Parallelize graph finalization#27629quic-calvnguy wants to merge 1 commit intomicrosoft:mainfrom
quic-calvnguy wants to merge 1 commit intomicrosoft:mainfrom
Conversation
Make graph finalization asynchronous Add threadpool, set default to 2
quic-calvnguy
commented
Mar 12, 2026
Contributor
Author
There was a problem hiding this comment.
base branch may be behind by a commit or two. will rebase
quic-calvnguy
commented
Mar 12, 2026
Contributor
Author
There was a problem hiding this comment.
This will be split up to .h/.cc once the PR is no longer a draft
quic-calvnguy
commented
Mar 12, 2026
Contributor
Author
There was a problem hiding this comment.
changes here will be removed.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Currently graph compilation for each fused node is done sequentially. However, the QNN finalization portion can be done asynchronously.
Motivation and Context
Sequential graph finalization increases total time of graph compilation. By asynchronously finalizing the graph, the total time for graph compilation and ORT session creation is expected to be faster