### Description
Improve the precision of tests.
Changes include:
(1) Update checkers.cc to use consistent default tolerance.
(2) Allow different default tolerances for different providers at
runtime (Previously, threshold of a test is decided during compiling).
(3) Explicitly set absolute and relative error tolerances for tests that
failed to pass new default threshold.
#### Default Thresholds Change
Note that the formula of testing is `abs(expected - value) < absolute +
relative * expected`
Default test thresholds when both absolute and relative tolerance are
not set:
type | provider | absolute (before) | absolute (after) | relative
(before) | relative (after)
-- | -- | -- | -- | -- | --
double | CPU | 0.001 | 0.00001 | 0 | 0.00001
double | CUDA | 0.005 | 0.00001 | 0 | 0.00001
double | TRT | 0.005 | 0.00001 | 0 | 0.00001
double | ROCM | 0.005 | 0.00001 | 0 | 0.00001
double | DML | 0.005 | 0.00001 | 0 | 0.00001
| | | | |
float | CPU | 0.0001 | 0.00001 | 0 | 0.0001
float | CUDA | 0.005 | 0.00001 | 0 | 0.0001
float | TRT | 0.005 | 0.00001 | 0 | 0.0001
float | ROCM | 0.005 | 0.00001 | 0 | 0.0001
float | DML | 0.005 | 0.00001 | 0 | 0.0001
float | Training* | 0.005 | 0.001 | 0 | 0.0001
| | | | |
half | CPU | 0.001 | 0.0025 | 0 | 0.001
half | CUDA | 0.005 | 0.0025 | 0 | 0.001
half | TRT | 0.005 | 0.0025 | 0 | 0.001
half | ROCM | 0.005 | 0.0025 | 0 | 0.001
half | DML | 0.02 | 0.005 | 0 | 0.001
half | Training* | 0.005 | 0.005 | 0 | 0.001
| | | | |
bfloat16 | CPU | 0.0001 | 0.02 | 0 | 0.01
bfloat16 | CUDA | 0.0001 | 0.02 | 0.05 | 0.01
bfloat16 | TRT | 0.0001 | 0.02 | 0.05 | 0.01
bfloat16 | ROCM | 0.0001 | 0.02 | 0.05 | 0.01
bfloat16 | DML | 0.0001 | 0.02 | 0.05 | 0.01
bfloat16 | Training* | 0.0001 | 0.02 | 0.05 | 0.01
*Training mean a build flag ENABLE_TRAINING_CORE is defined. The
provider can be any one.
#### Threshold for provider
Previously, the threshold might change according to build flags:
```
#if defined(USE_CUDA) || defined(USE_ROCM) || defined(USE_DML)
constexpr float threshold = 0.005f;
#else
constexpr float threshold = 0.0001f;
#endif
```
For a cpu only build, the threshold is 0.0001. For a cuda build, the
threshold for CPU provider (some tests in cuda build actually run with
CPU provider) is changed to 0.005.
After this change, the threshold only depends on data type and provider
used in the test. It will not change by build flags for non-training
builds.
Default thresholds for training might be different from inference
(please refer to the above table). There are a few factors there:
Training has gradient outputs; TF32 is not disabled in training; Some
training tests has iterations, and error might accumulate. How to set
different thresholds based on these factors could be a future task.
Currently, the nhwc_transformer_test.cc compilation unit defines
explicit FP16 versions of `ModelTestBuilder::MakeInput<MLFloat16>` and
`ModelTestBuilder::MakeInitializer<MLFloat16>` outside of the
ModelTestBuilder class's header file.
These explicit template instantiations cause linker errors when other
compilation units also instantiate these functions due to duplicate
definitions. Additionally, the versions defined in
nhwc_transformer_test.cc do not really conform to the expected behavior
in the original ModelTestBuilder class, which is to make random
input/initializer values. Instead, the versions in
nhwc_transformer_test.cc create a range of values.
The solution is to edit nhwc_transformer_test.cc to use stand-alone
static functions that do not change the ModelTestBuilder class.
**Note**: This linker error cannot currently be replicated in our CIs
because it requires a QNN-HTP-enabled Windows ARM64 environment with
`MLAS_F16VEC_INTRINSICS_SUPPORTED` defined. I can replicate on a local
build. The linker error/conflict happens with with this new FP16 QNN
test:
d4c8bc359e/onnxruntime/test/providers/qnn/clip_op_test.cc (L186)
### Description
The docker image name was fixed, but the docker argument was different
in different job.
It would trigger rebuilding the docker image almost every time!!!
### Description
<!-- Describe your changes. -->
- [x] Pad operator has introduced a new input called "axes" which
specifies which axis to pad. But it defaults to input_rank if axes is
not provided which was the behavior before the opset upgrade.
- [x] ReduceMean
- [x] ReduceL2
- [x] ReduceLogSumExp
- [x] ReduceSum
- Reduction ops all had the axes attribute switched to an input and a
new attribute called "noop_with_empty_axes" was added to define what to
do when axes is not specified.
- [x] Resize has had two new attributes introduced: antialias and
keep_aspect_ratio_policy. From Operators.md I've gathered:
"Antialiasing is achieved by stretching the resampling filter by a
factor max(1, 1 / scale), which means that when downsampling, more input
pixels contribute to an output pixel."
keep_aspect_ratio_policy "describes how to interpret the `sizes` input
with regard to keeping the original aspect ratio of the input." there
are a couple enum-type options that specify different policies and what
to do in each case.
- NOTE: Baiju already included opset18 tests in
https://github.com/microsoft/onnxruntime/pull/17772
- [x] ScatterElements/ScatterND has had a new attribute introduced
called "reduction." This specifies the type of reduction to apply: none
(default), add, mul, max, min.
- [x] Split introduced a new attribute called "num_outputs" which
specifies how many outputs to split the input tensor into. This is in
contrast to the previous, default behavior of specifying a "split" input
which defines the size of each resultant tensor of the output.
### 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. -->
Operator or model test result shall not depend on whether
NVIDIA_TF32_OVERRIDE environment variable is set or not. This make test results more deterministic.
### Description
<!-- Describe your changes. -->
This change addresses the following issues with the current CustomOP
Output Type inference
- The function does not take into account optional inputs. When input is
absent the inference is silently aborted, and no output type is inferred
(P1 customer issue)
- Inferring output type based on the input type for multi-kernel custom
ops is done based on the latest in sequence kernel definition. There is
not an attempt made to match the kernel based on the input type.
- Inference is aborted when variadic inputs/outputs are detected when
the generated input/output names fail to obtain type constraints. This
is not immediately clear from the code, because custom op schema is not
available within the inference function.
- No error reporting.
### 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. -->
Most of CustomOPs lack their own type and shape inference function as it
was recently introduced. For that reason, it is important to fix this.
This change is inspired by a customer issue.
This is a follow up on:
- https://github.com/microsoft/onnxruntime/pull/15184
- https://github.com/cbourjau/ort-custom-op/pull/11
- https://github.com/microsoft/onnxruntime-extensions/issues/451
Bumps
[follow-redirects](https://github.com/follow-redirects/follow-redirects)
from 1.15.4 to 1.15.6.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="35a517c586"><code>35a517c</code></a>
Release version 1.15.6 of the npm package.</li>
<li><a
href="c4f847f851"><code>c4f847f</code></a>
Drop Proxy-Authorization across hosts.</li>
<li><a
href="8526b4a1b2"><code>8526b4a</code></a>
Use GitHub for disclosure.</li>
<li><a
href="b1677ce001"><code>b1677ce</code></a>
Release version 1.15.5 of the npm package.</li>
<li><a
href="d8914f7982"><code>d8914f7</code></a>
Preserve fragment in responseUrl.</li>
<li>See full diff in <a
href="https://github.com/follow-redirects/follow-redirects/compare/v1.15.4...v1.15.6">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/microsoft/onnxruntime/network/alerts).
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps
[follow-redirects](https://github.com/follow-redirects/follow-redirects)
from 1.15.4 to 1.15.6.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="35a517c586"><code>35a517c</code></a>
Release version 1.15.6 of the npm package.</li>
<li><a
href="c4f847f851"><code>c4f847f</code></a>
Drop Proxy-Authorization across hosts.</li>
<li><a
href="8526b4a1b2"><code>8526b4a</code></a>
Use GitHub for disclosure.</li>
<li><a
href="b1677ce001"><code>b1677ce</code></a>
Release version 1.15.5 of the npm package.</li>
<li><a
href="d8914f7982"><code>d8914f7</code></a>
Preserve fragment in responseUrl.</li>
<li>See full diff in <a
href="https://github.com/follow-redirects/follow-redirects/compare/v1.15.4...v1.15.6">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/microsoft/onnxruntime/network/alerts).
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps
[follow-redirects](https://github.com/follow-redirects/follow-redirects)
from 1.15.4 to 1.15.6.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="35a517c586"><code>35a517c</code></a>
Release version 1.15.6 of the npm package.</li>
<li><a
href="c4f847f851"><code>c4f847f</code></a>
Drop Proxy-Authorization across hosts.</li>
<li><a
href="8526b4a1b2"><code>8526b4a</code></a>
Use GitHub for disclosure.</li>
<li><a
href="b1677ce001"><code>b1677ce</code></a>
Release version 1.15.5 of the npm package.</li>
<li><a
href="d8914f7982"><code>d8914f7</code></a>
Preserve fragment in responseUrl.</li>
<li>See full diff in <a
href="https://github.com/follow-redirects/follow-redirects/compare/v1.15.4...v1.15.6">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/microsoft/onnxruntime/network/alerts).
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
### Description
<!-- Describe your changes. -->
Add `cann_dependencies`
### 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. -->
The previous [PR](https://github.com/microsoft/onnxruntime/pull/17365)
avioded using patchelf but lost `cann_dependencies`, This PR adds
`cann_dependencies` to avoid require cann libraries when repairing
wheel.
### Description
Fix a few warnings in typedoc (for generating JS API):
```
[warning] The signature TrainingSession.loadParametersBuffer has an @param with name "buffer", which was not used.
[warning] NonTensorType, defined in ./lib/onnx-value.ts, is referenced by OnnxValue but not included in the documentation.
[warning] TensorFactory, defined in ./lib/tensor-factory.ts, is referenced by Tensor but not included in the documentation.
[warning] ExternalDataFileType, defined in ./lib/onnx-model.ts, is referenced by InferenceSession.SessionOptions.externalData but not included in the documentation.
[warning] TensorToDataUrlOptions, defined in ./lib/tensor-conversion.ts, is referenced by Tensor.toDataURL.toDataURL.options but not included in the documentation.
[warning] TensorToImageDataOptions, defined in ./lib/tensor-conversion.ts, is referenced by Tensor.toImageData.toImageData.options but not included in the documentation.
[warning] Failed to resolve link to "GpuBufferType" in comment for Env.WebGpuFlags.adapter.
[warning] Failed to resolve link to "GpuBufferType" in comment for Env.WebGpuFlags.device.
```
Changes highlighted:
- Merge `CoreMlExecutionProviderOption` and
`CoreMLExecutionProviderOption`. They expose 2 set of different options
for React-native and ORT nodejs binding. This should be fixed in future.
- Fix a few inconsistency of names between JSDoc and parameters
- Fix broken type links
- Exclude trace functions
### Description
Fix#19931 broken Get Started link
HTTP 404 for "Get Started" link in "ONNX Runtime JavaScript API" page
Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com>
fix: "UserWarning: Unsupported Windows version (11). ONNX Runtime
supports Windows 10 and above, only."
### Description
Include Windows 11 in the version check. Now, you will not see the
warning “Unsupported Windows version (11). ONNX Runtime supports Windows
10 and above, only.”
### Motivation and Context
Warning on Windows 11: Only supports systems above Windows 10, which is
somewhat strange.
### Description
This PR rewrite the backend resolve logic to support specifying multiple
EPs.
#### Backend
The first version of ONNX Runtime Web actually carried some existing
code from [ONNX.js](https://github.com/microsoft/onnxjs), which includes
the "backend" concept. The original "backend" in ONNX.js is designed in
a way assuming there is only one backend from user's backend hint list
will be used. For example, in ONNX.js, if user specify a backend hint as
`['webgl', 'wasm']`, ONNX.js will first try to use WebGL backend - if it
loads successfully (the browser supports webgl), then "webgl" backend
will be used and "wasm" will be ignored; otherwise, "webgl" will be
ignored and try to load "wasm" backend.
In short: only one backend will be used when initializing a session.
#### Execution Provider
Execution Provider, or EP, in ONNX Runtime is a different concept. One
of the differences is that users are allow to specify multiple EPs, and
if one does not support a particular kernel, it can fallback to other
EP. This is a very common case when using a GPU EP in ONNX Runtime.
#### Current Status: Backend v.s. EP
Because of the history reasons mentioned above, the current status is
quite confusing. There are **real backend**s, which means it's different
implementation in code; and there are **backend hint**s, which are used
as string names for backend hint; and there are **EP**s of the ONNX
Runtime concepts.
currently there are only 2 **backend**s in our code base: The "onnxjs
backend", and the "wasm backend". The "onnxjs backend" currently only
powers backend hint "webgl", which go into the old onnx.js code path.
All other backend hints including "wasm", "cpu"(alias to wasm), "webgpu"
and "webnn" are all powered by "wasm backend".
And because ORT Web treat "backend" as an internal concept and want to
align with ONNX Runtime, so those names of backend hints are becoming EP
names.
The following table shows today's status:
| Execution Provider Name (public) / Backend Hint (internal) | Backend |
EP in ORT
| -------- | ------- | ------- |
| "wasm"/"cpu" | WasmBackend | CPU EP
| "webgl" | OnnxjsBackend | \* technically not an EP
| "webgpu" | WasmBackend | JSEP
| "webnn" | WasmBackend | WebNN EP
#### Problem
While the API allows to specify multiple EPs, the backend resolving only
allows one backend. This causes issues when user specify multiple EP
names in session options, the backend resolve behavior and EP
registration behavior is inconsistent. Specifically, in this issue:
https://github.com/microsoft/onnxruntime/issues/15796#issuecomment-1925363908:
EP list `['webgpu', 'wasm']` on a browser without WebGPU support
resolves to 'wasm' backend, but the full EP list is passed in session
options, so JSEP is still enabled, causing the runtime error.
#### Solution
Since we still need WebGL backend, we cannot totally remove the backend
register/resolve system. In this PR I made the following changes:
- initialize every backend from the EP list, instead of only do that for
the first successful one.
- for the first resolved backend, filter all EP using the exact same
backend. Remove all EPs not using this backend from session options
- for every explicitly specified EP, if it's removed, show a warning
message in console
### Description
<!-- Describe your changes. -->
* Add concurrency test to EP Perf CI panel (impl. by onnx_test_runner)
* Model: FasterRCNN-10 model within CI image
* `-c` param configurable via CI panel when kicking off CI tasks
* Auto-replicate test input/outputs according to `-c` param
* By default, the model test will be executed in 100 iterations (~2min
added to T4 CI task load overall)
### 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. -->
To monitor potential concurrency issues of ORT-TRT
### Description
If the `K` value is flowing through as a tensor, we are updating a
mutable member of the `TopK` class and basing the compute off that -
which is likely to cause data race issues with concurrent Run() calls
and `K` value changes.
### Motivation and Context
Fix potential race in CUDA TopK kernel
### Description
Modifications to support 2GB+ checkpoint & Upgrading Flatbuffers
### Motivation and Context
This PR includes changes that will make ort handle 2GB+ checkpoints.
To do that we need to upgrade flatbuffers to 23.5.9 -
https://github.com/google/flatbuffers/pull/7945
- Modified the commitHash and the hash for the new version
- Removed the patch for rust generator's unused variable warning as it
is no longer producing this - [Check it out
here](d121e09d89/src/idl_gen_rust.cpp)
- Updated the VerifyField calls with alignment values that were
introduced in the new version.
---------
Co-authored-by: Sumit Agarwal <sumitagarwal@microsoft.com>
### Description
1. Use stage to organize the pipeline and split building and testing
2. Move compilation on CPU machine
3. test stage can leverage existing artifacts
4. check wheel size, it gives warning if the size above 300M
5. docker image name wasn't change even the argument changed, which
caused the docker image was always rebuilt. So update the docker image
name according to the argument can save the docker build time.
Pipeline duration reduced by 60% (2 hours -> 50 minutes)
Compilation time reduced by 75% (1.5hours -> 20 minutes)
GPU time reduced by 87% ( 8 hours to 1 hours)
for debugging, the GPU time could be reduced by above 95%, because we
can choose run only one test stage and skip building.
### Motivation and Context
Make the pipeline efficient.
Optimized
https://dev.azure.com/aiinfra/Lotus/_build/results?buildId=424177&view=results
Curent
https://dev.azure.com/aiinfra/Lotus/_build/results?buildId=422393&view=results
---------
### Description
Change nuget pipeline's "Final_Jar_Testing_Windows_GPU" job to download
TRT binaries in every build. Now all the other build jobs are already
doing this. This is the only one left.
Similar to #19909
### Motivation and Context
As a follow up of #19118
Update stable diffusion demo to add options `--max-cuda-graphs` and
`--user-compute-stream`.
* Add python class GpuBindingManager to manage IO Binding based on input
shape and max number of cuda graphs setting. The benefit is that one
inference session could enable or disable cuda graph in different runs.
* When `--user-compute-stream`, the demo will use custom compute stream.
### Description
Add a patch for Windows ARM64EC
### Motivation and Context
Will need more changes in onnxruntime/core/common/cpuid_arch_definition.h and onnxruntime/core/common/cpuid_info.cc
### Description
Change nuget pipeline's "Final_Jar_Testing_Windows_GPU" job to download
TRT binaries in every build. Now all the other build jobs are already
doing this. This is the only one left.
### Motivation and Context
As a follow up of #19118
### Description
<!-- Describe your changes. -->
Add 2 C API for ORT extension:
- KernelInfo_GetAllocator
- OrtCustomOp::GetMayInplace
### 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. -->
Add 2 C API for ORT extension project, which will leverage these 2 APIs
for GroupQueryAttention custom op.
### Refine logging for execution plan print
Printing NodeIndex only is not enough for us to debug the execution
order.
keep original behaviour for ORT_MINIMAL_BUILD build in case of any CPU
memory concerns.
### 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
<!-- Describe your changes. -->
Update to .net8. Didn't want to build with the latest VS2022 using net6
(which was EOL last year).
### 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. -->
Building onnxruntime ROCm EP with --enable_nccl --use_mpi fails due to
inclusion of MOE source files but MOE is not supported. The error
observed is
`error: contrib_ops/rocm/moe/ft_moe/moe_kernel.h: No such file or
directory`
The fix is to exclude collective/sharded_moe.* files when nccl is
requested.
### Description
Copies the `QNN_HOME/lib/hexagon-v73/unsigned/libqnnhtpv73.cat` file
from QNN SDK to the unittest build directory. This is necessary in order
to be able to load the `libQnnHtpV73Skel.so` file on Windows for modern
versions of QNN SDK.
### Motivation and Context
A [digitally-signed catalog
file](https://learn.microsoft.com/en-us/windows-hardware/drivers/install/catalog-files)
(.cat) can be used as a digital signature for an arbitrary collection of
files.
### Description
<!-- Describe your changes. -->
add new API KernelContext_GetScratchBuffer to get scratch buffer from
kernel context
### 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. -->
add new API KernelContext_GetScratchBuffer to get scratch buffer from
kernel context which will be used in ORT extension project for
GroupQueryAttention custom op
### Description
This PR updates the replacement of MultiHeadAttention (MHA) with
GroupQueryAttention (GQA). It is related to the changes in [this
PR](https://github.com/microsoft/onnxruntime/pull/18906).
### Motivation and Context
The updated replacement of MHA with GQA includes the following fusion
changes.
- Apply sliding window within GQA
- Fuse the rotary embeddings within GQA
- Fuse the 3 MatMuls into 1 packed MatMul if possible
- Fuse the 3 Adds into 1 packed Add if possible
### Description
GQA Rotary Dimension 1 incorrectly assumed to be based on head size.
### Motivation and Context
This change should enable us to run phi-2 with GQA and Rotary Embedding
fused.
### Description
the `npm test` flags are difficult to memorize, because they are
different to the `ort.env` flags. This change makes those flags align
with ort JS API. eg. `--wasm-enable-proxy` became `--wasm.proxy`.
Old flags are marked as deprecated except `-x` (as a shortcut of
`--wasm.numThreads`)
