Multi-partition support for context binary cache feature#18865
Merged
Multi-partition support for context binary cache feature#18865
Conversation
1. dump model part
-- Validate QNN context model with graph partition result from QDQ model -- In Compile(), load the QNN context model, get all the EPContext node, create QNN context from context binary, create QNN graph from the binary, and execute
…th, qnn_context_embed_mode. Add session option accordingly.
HectorSVC
commented
Dec 18, 2023
include/onnxruntime/core/session/onnxruntime_session_options_config_keys.h
Outdated
Show resolved
Hide resolved
…o session options
HectorSVC
added a commit
that referenced
this pull request
Dec 20, 2023
Move QNN EP provider options to session options ### Description Need to use session option to support multi-partition for context cache feature. To smooth the transaction, move the provider options to session options first. This is the first step for PR: PR #18865
HectorSVC
added a commit
that referenced
this pull request
Jan 19, 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
HectorSVC
commented
Jan 22, 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
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
…node will fallback on CPU EP. Add with float32 runs on Linux with HTP backend simulator, that's why it failed.
adrianlizarraga
approved these changes
Feb 1, 2024
rohan11235813
pushed a commit
to quadric-io/onnxruntime
that referenced
this pull request
Aug 19, 2025
… 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. microsoft/onnxruntime#18865
rohan11235813
pushed a commit
to quadric-io/onnxruntime
that referenced
this pull request
Sep 15, 2025
… 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. microsoft/onnxruntime#18865
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
2 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.
Description
Multi-partition support for context binary cache feature
Motivation and Context
It only support single partition before this changes. There's graph partition limitation for context cache feature after this change.