Sync with Microsoft ONNX Runtime - 31/07/2025 #764
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
…me (microsoft#25516) After cherry-picking from win-onnxruntime (microsoft#25481), the MIGraphX EP stopped compiling on the main branch.
### Description This PR enhances unidirectional `FlashAttention` by applying causal masking inside the main loop. This optimization eliminates unnecessary memory loads by avoiding future entries in the KV cache. Testing on Lunar Lake shows up to a 20% performance improvement for `phi-4-mini-accuracy4` (with a prompt of 4096). Similar performance gains were also observed for other models, including `Qwen3-0.6B-accuracy4`. This PR now uses the more readable `unidirectional` attribute instead of `is_gqa`, to control causal masking. ### Motivation and Context See above.
…ttr name (microsoft#25565) ### Description Updates `Node_GetAttributeByName` to return an error status with code `ORT_NOT_FOUND` and set the `attribute` output parameter to `NULL` when called with a non-existing attribute name. Why? Currently, a caller has to do string comparison of the `OrtStatus` error message to determine if the attribute does not exist or if another error occurred. This can be somewhat cumbersome. With this change, the caller can just check the error code. ### Motivation and Context Make it easier to use `Node_GetAttributeByName`.
### Motivation and Context Fix data type check to skip optional I/Os. Optional inputs/outputs would have empty name, and it's valid ONNX syntax. Without this fix, any model with optional inputs/outputs would fail the check due to missing protobuf fields. Without this fix, we'd hit error fetching `elem_type` from protobuf. ``` 2025-07-22 11:14:40.117740035 [I:onnxruntime:, qnn_execution_provider.cc:740 GetSupportedNodes] Validation FAILED for 1 nodes in NodeUnit (Pad) : Operator type: Pad Node name: /blocks.4/Pad Node index: 176 REASON : The tensor doesn't have elem_type. ```
…#25581) [QNN-EP] Einsum equation ReduceSum Multiply on broadcast X
### Description This change fixes the problem when building Dawn monolith library, it failed to pick the correct imported abseil library. Now we separate the triplet files into per-config to avoid this problem.
### Description Update OrtEpFactory in new EPs to add allocator, data transfer and stream stubs. ### Motivation and Context
### Description For f16 uniform variables, use u32 to bit-wise represent them. ### Motivation and Context Some devices supports f16 in shader/storage buffer, but not in uniform buffers. Dawn will set the f16_support to false for them. However, we don't necessarily have to use f16 in uniform. This change together with microsoft#25349 will enable using f16 models on some Android devices.
### Description Add a new `Node_GetTensorAttributeAsOrtValue` API to support attribute that is a `TENSOR` type. This API returns a const OrtValue that represents the TensorProto in the `TENSOR `attribute.
### Description ~~Remove the out-of-dated patch file.~~ Remove the changes of `src/arm/windows/init.c` from the patch file. Changes of `include/cpuinfo.h` is kept.
### Description - Add a GraphTransformer `WhereDummyDq` to insert dummy DequantizeLinear on Where node's initializer input to form a Node Unit when Where node has one DQ and one scalar initializer input - Add corresponding unit test for the optimization ### Motivation and Context - To reduce the additional Dequantize and Quantize nodes, we would like to pass `WhereNodeGroupSelector::Check`.
ankitm3k
approved these changes
Jul 31, 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.