Sync with Microsoft ONNX Runtime - 12/08/2025 #775
Merged
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
microsoft#25699) ### Description This change should be included in PR microsoft#25616. I missed it. ### Motivation and Context Currently our iOS packaging pipeline is failing because of this.
### Description - Trivial changes to support LoongArch Java API build ### Motivation and Context - ONNX Runtime already supports LoongArch, but the Java API requires some trivial changes to enable it.
### Description It is related to microsoft#25320 microsoft#23979. Enable tensor raw data sharing for externalized tensor proto with kTensorProtoMemoryAddressTag ### Motivation and Context With microsoft#25320 microsoft#23979, all initialized tensor protos are associated with OrtValue, VitisiAI EP need to adapt to this change. Co-authored-by: mingyue <[email protected]>
… Linux (microsoft#25704) ### Description fixes microsoft#25700 --------- Co-authored-by: Copilot <[email protected]>
A set of changes required for WCR/WindowsML that were added to the MIGraphX Execution provider. The development was done in the ROCm repository, now we want to sync with the main branch with a single drop. The PR incorporates the review comments from the previous closed PR microsoft#25338. Motivation and Context Fixes, changes, and updates to MIGraphX EP that have been done for ROCm development. Pushing this back upstream to ensure mainline onnxruntime is using the latest changes. Moving forward, MIGraphX EP will be cut from the latest official release tag as a base point while also adding additional features that will be contributed back. --------- Co-authored-by: urpetkov-amd <[email protected]> Co-authored-by: Ted Themistokleous <[email protected]> Co-authored-by: Ted Themistokleous <[email protected]> Co-authored-by: Scott McKay <[email protected]>
…ft#25693) ### Description Add --use_vcpkg_ms_internal_asset_cache to webgpu CI ### Motivation and Context to make it consistent with all other CIs
### Description <!-- Describe your changes. --> ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. -->
### Description Retrieve Device and Command buffer for DML to inject other gfx command into the same device and command buffer for efficient GPU pipelining ### Motivation and Context Retrieve Device and Command buffer for DML to inject other gfx command into the same device and command buffer for efficient GPU pipelining
### Description add usage of `ReadonlyAllocator` for WebGPU EP ### Motivation and Context `ReadonlyAllocator` is added in microsoft#25348 to allow an EP to register a separated allocator only use for initializers. WebGPU EP already has different handling to initializers and non-initializers, and this change makes WebGPU EP to use the preferred way to deal with it. Now the allocator depends on the `OrtAllocatorType` instead of the session initialization status.
…xisting list-valued options to use argparse "extend" action. (microsoft#25718) ### Description <!-- Describe your changes. --> - Add build.py `--targets` option to specify multiple targets. - Update existing list-valued options to use argparse "extend" action. Unlike "append", "extend" won't create nested lists. ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> Allow multiple targets to be specified. Use newer argparse feature to simplify option handling.
ankitm3k
approved these changes
Aug 12, 2025
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.
Description
Synchronizing intel/onnxruntime ovep-develop branch with latest changes from microsoft/onnxruntime master branch.