Compile API: disable optimizations by default

[adrianlizarraga]

Description

• Disables graph optimizations by default when using the explicit compiling API.
• Adds ModelCompilationOptions_SetGraphOptimizationLevel to allow the user to set an optimization level.
• Adds C++, Python, and C# bindings for the new API function.
• Updates ModelCompilationOptions_SetFlags to take in a uint32_t flags parameter instead of size_t flags to ensure the same size across platforms. This API is not yet in a public ORT release, so safe to modify.

Motivation and Context

When compiling, prefer allowing the EP to do the optimizations instead of ORT.

[Copilot]

Pull Request Overview

This PR disables graph optimizations by default in the explicit compiling API, preferring to let execution providers handle optimizations instead. It adds a new method to allow users to manually enable optimizations when needed.

• Changes the default graph optimization level to TransformerLevel::Default (minimum optimizations) instead of the previous behavior
• Adds ModelCompilationOptions_SetGraphOptimizationLevel API to allow users to explicitly set optimization levels
• Updates test expectations to account for different EPContext node input counts based on optimization settings

Reviewed Changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
onnxruntime/core/session/model_compilation_options.h	Declares new SetGraphOptimizationLevel method
onnxruntime/core/session/model_compilation_options.cc	Implements optimization level setting and sets default to L0
onnxruntime/core/session/compile_api.h	Declares C API wrapper for graph optimization level setting
onnxruntime/core/session/compile_api.cc	Implements C API wrapper function
include/onnxruntime/core/session/onnxruntime_c_api.h	Adds C API function declaration and documentation
include/onnxruntime/core/session/onnxruntime_cxx_api.h	Adds C++ wrapper method declaration
include/onnxruntime/core/session/onnxruntime_cxx_inline.h	Implements C++ wrapper method
onnxruntime/test/providers/qnn/qnn_ep_context_test.cc	Updates tests to handle different optimization behaviors and add explicit optimization setting

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}