### Description
Fixes build failure for the cuda minimal build




### 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. -->
[This change](#19470) in
1.20 is causing build failures for the cuda minimal build.
Essentially, some cudnn logic was not guarded by the `USE_CUDA_MINIMAL`.
Also the build is looking for cudnn while in the cuda minimal build it
shouldn't depend on it, resulting in linking error.


cc @gedoensmax @chilo-ms

### Description
Fixes build failure for the cuda minimal build




### 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. -->
[This change](microsoft#19470) in
1.20 is causing build failures for the cuda minimal build.
Essentially, some cudnn logic was not guarded by the `USE_CUDA_MINIMAL`.
Also the build is looking for cudnn while in the cuda minimal build it
shouldn't depend on it, resulting in linking error.


cc @gedoensmax @chilo-ms

### Description
Fixes build failure for the cuda minimal build




### 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. -->
[This change](microsoft#19470) in
1.20 is causing build failures for the cuda minimal build.
Essentially, some cudnn logic was not guarded by the `USE_CUDA_MINIMAL`.
Also the build is looking for cudnn while in the cuda minimal build it
shouldn't depend on it, resulting in linking error.


cc @gedoensmax @chilo-ms

### Description
Fixes build failure for the cuda minimal build

### 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. -->
[This change](microsoft#19470) in
1.20 is causing build failures for the cuda minimal build.
Essentially, some cudnn logic was not guarded by the `USE_CUDA_MINIMAL`.
Also the build is looking for cudnn while in the cuda minimal build it
shouldn't depend on it, resulting in linking error.

cc @gedoensmax @chilo-ms

(cherry picked from commit bbe7c87)

[ARM] MatMulNBits Fp16 support - API change only (microsoft#22826)

A break-down PR of microsoft#22651
Op API change only.
- add template to functions and classes that support fp32 and fp16
- rename functions, classes and files that support fp32 and fp16 from
SQNBxxx to QNBxxx

<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

Change-Id: Ib489e7858d42abcbe0514ac44e4d2172e32384a3

Re-enable test symbolic shape infer (microsoft#22737)

<!-- Describe your changes. -->
It seems after CI updated to py310, numpy got updated to 2.0 and sympy
1.2 failed to cast float numpy array.
Pointing sympy to 1.13 when py>=3.9 and re-enable unit test

<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
Error: Linux CPU
CI

[Quant tool] Handle input models with pre-quantized weights (microsoft#22633)

Allows the QDQ quantizer to handle input models that already have some
pre-quantized weights. In this case, the qdq quantizer will properly
skip/handle the pre-quantized weights.

Also handles an operator (e.g., Conv) with a pre-quantized weight and a
float bias. The tool will read the pre-quantized weight's quantization
scale to compute the bias's scale (`bias_scale = input_scale *
weight_scale`).

Input model (pre-quantized Conv weight):

![image](https://github.com/user-attachments/assets/7d2626e4-49ad-47ae-bd0e-6339ac590435)

Output QDQ model (everything is quantized):

![image](https://github.com/user-attachments/assets/393804d3-f042-47bd-895f-3d667fb2ae94)

Customers may use external tools to quantize some weights (e.g., int4
for Conv/MatMul). The qdq quantizer should still be able to quantize the
rest of the model (float weights and activations) in this case.

Update Gradle version 8.7 and java version 17 within onnxruntime/java (microsoft#22771)

This change is to update the Gradle version within java project to 8.7,
it also upgrades the JAVA to 17. Gradle version from react-native was
also updated to 7.5 to make it compatible with changes from the Java
directory. However, the target java version remains the same. Java
version from these will be upgraded in a separated PR.

This is spited from microsoft#22206

This is the first step to upgrade the react native version.

Ovep develop 1.21 (microsoft#22824)

OVEP development changes for ORT 1.21 Release

Has critical bug fixes
Support for concurrency execution of models is enabled
Support for OV 2024.5
Memory optimizations for NPU platform

---------

Co-authored-by: jatinwadhwa921 <[email protected]>
Co-authored-by: Ankit Maheshkar <[email protected]>
Co-authored-by: sfatimar <[email protected]>
Co-authored-by: saurabhkale17 <[email protected]>
Co-authored-by: TejalKhade28 <[email protected]>
Co-authored-by: Javier E. Martinez <[email protected]>

Fix 1.20 cuda minimal build failure (microsoft#22751)

Fixes build failure for the cuda minimal build

<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
[This change](microsoft#19470) in
1.20 is causing build failures for the cuda minimal build.
Essentially, some cudnn logic was not guarded by the `USE_CUDA_MINIMAL`.
Also the build is looking for cudnn while in the cuda minimal build it
shouldn't depend on it, resulting in linking error.

cc @gedoensmax @chilo-ms

[ARM] MatMulNBits fp16 support - connect kernels (microsoft#22856)

A breakdown PR of microsoft#22651

<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

Change-Id: I3014c1002ff375a507bc04de7756baacf9a2b77a

[WebNN EP] Support Einsum op (microsoft#19558)

Adds support for einsum via WebNN matmul, transpose, reshape, reducesum,
identity and element-wise binary ops.

Refactor SkipLayerNorm and handle beta properly (microsoft#22862)

Signed-off-by: Liqun Fu <[email protected]>
Signed-off-by: Liqun Fu <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Change-Id: Ic5b8a6eb775542a57f07f5e593cc399dd7eeaa8f

Fix CUDA/DML package exception caused by ENABLE_CUDA_NHWC_OPS (microsoft#22851)

Now,  ENABLE_CUDA_NHWC_OPS is enabled by default.
It adds a new chance to create cuda provider while both cuda/dml are
enabled

<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

Optimize Transpose around QLinearSoftmax (microsoft#22849)

<!-- Describe your changes. -->

- Improved Transpose around QLinearSoftmax in Level 3 NHWC Transformer.
- Removed redundant code HandleQLinearConcat, HandleQLinearBinaryOp.

<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

By merging and eliminating redundant transpose , the Image Segmentation
i8 model (MobileNetv2 + DeepLabv3) achieves a 2.34X speedup.

Replace INFINITY by std::numeric_limits<float>::infinity() (microsoft#22868)

Replace INFINITY by `std::numeric_limits<float>::infinity()` to avoid
build errors with Visual Studio 2022 v17.12 Preview 5

microsoft#22728

[js/webgpu] Optimize transpose as reshape when suitable (microsoft#22870)

BUG microsoft#22031

Change-Id: I6c70d84228f1563792218c6c3c18b023852d4147

clang format code

Change-Id: I422a9474da9e9cfc9ac8819569a13520c5d2641f