### Description
Previously we wanted to add DirectML EP to existing onnxruntime Windows
CUDA packages. After careful consideration, we will postpone the change.
This PR reverts some pipeline changes previously made by @mszhanyi and
@jchen351 .
### 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
Add a new stage to build cuda and dml in Windows GPU CI pipeline (PR
checks) to prevent regressions introduced by new cuda tests.
Update all tests in cuda/testcases name prefix to CudaEp for skipping
them easily
### Motivation and Context
1. CudaNhwcEP is added by default when using cuda ep
2. if onnxruntime_ENABLE_CUDA_EP_INTERNAL_TES is enable, the tests in
tests/provider/cuda/testcases is added too.
### To do
add enable_pybind in the new stage.
Now, --enable_pybind will trigger some python test, like
onnxruntime_test_python.py.
It uses the API of get_avaible_providers() .
More discussions are needed to decide how to make it works
…ime/java (#22771)"
This reverts commit 632a36a233.
### Description
<!-- Describe your changes. -->
### Motivation and Context
Run E2E tests using Browserstack failed due to this PR.
### Description
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 #22206
### Motivation and Context
This is the first step to upgrade the react native version.
### Description
Now, we need to build cuda and dml in one package.
But CUDA EP and DML EP can't run in one process.
It will throw the exception of `the GPU device instance has been
suspended`
So the issue is CUDA EP and DML EP coexist in compile time but can't
exist in run time.
This PR is to split cuda ep test and dml ep test in all unit tests.
The solution is to use 2 environment variable, NO_CUDA_TEST and
NO_DML_TEST, in CI.
For example, if NO_CUDA_TEST is set, the DefaultCudaExecutionProvider
will be nullptr, and the test will not run with CUDA EP.
In debugging, the CUDAExecutionProvider will not be called.
I think, as long as cuda functions, like cudaSetDevice, are not called,
DML EP tests can pass.
Disabled java test of testDIrectML because it doesn't work now even
without CUDA EP.
### Description
Increanse TensorRT tolerance from default 1e-5 to 1e-3 after TRT 10.4
### 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
Java parts of Multi-LoRA support - #22046.
### Motivation and Context
API equivalence with Python & C#.
---------
Co-authored-by: Dmitri Smirnov <dmitrism@microsoft.com>
- Add Java API for appending QNN EP
- Update Java unit test setup
- Fix issues with setting system properties for tests
- Unify Windows/non-Windows setup to simplify
### Description
Following from #16578 and #16835 this migrates over
`OnnxTensor.createTensor(<array>)` to first instantiate a
`java.nio.Buffer` and then copy the array into that buffer in Java
before creating the tensor. It also changes the `OnnxTensor.getValue()`
method which returns a multidimensional array so it does the array
construction and value copy in Java. This allows the removal of some
unpleasant recursive C code which repeatedly calls into the JVM to
traverse Java's arrays. The equivalent Java code is still unpleasant and
recursive, but it's easier to reason about and memory safe. As a bonus,
more `OnnxTensor`s are now backed by buffers which allow users to pin
memory and reduce allocations by reusing them for same sized inputs.
Some of the JNI code which parses Java arrays still exists as it's used
by `OnnxMap`, removing that will be the target of a future refactor.
Strings are still processed in JNI as it is easier to work with String
tensors and UTF-8 arrays in C.
### Motivation and Context
Minimizing the amount of JNI code makes it easier to maintain and using
buffers in preference to arrays allows for fewer allocations.
### Description
Adds support for constructing an `OrtSession` from a
`java.nio.ByteBuffer`. These buffers can be memory mapped from files
which means there doesn't need to be copies of the model protobuf held
in Java, reducing peak memory usage during session construction.
### Motivation and Context
Reduces memory usage on model construction by not requiring as many
copies on the Java side. Should help with #19599.
### Description
Fixes a bug where the buffer offset and position was incorrectly
computed if the user supplied a `ByteBuffer` to `createTensor` but set
the type of the tensor to something other than `INT8`. This would be
more common if the user was trying to load the initializers from a
serialized representation and didn't want to bother with the type
information (which is the case in #21321).
### Motivation and Context
Partial fix for #21321. The remainder of the fix is to add a helper
which allows users to load initializers out of an `onnx_data` file, but
that will require adding protobuf as a dependency for the Java API to
allow the parsing of an ONNX file separately from the native code. It
might be nicer to put that functionality into ORT's C API so it can
return the lengths & offsets of the initializers when provided with an
ONNX file containing external initializers. We hit this kind of thing in
Java more often than other languages as in Java models can be supplied
as classpath resources which we can easily read, but not materialize on
disk for the ORT native library to read.
# Description
This PR removes the building of the ORT "mobile" packages and much of the associated infrastructure which is no longer needed.
Not removed yet - tools/ci_build/github/android/mobile_package.required_operators.config and the helper scripts that depend on it.
# Motivation and Context
The mobile packages were deprecated in 1.18. Users should use the full packages (Android - onnxruntime-android, iOS - onnxruntime-c/onnxruntime-objc) instead or do a custom build.
### Description
I misunderstood how UpdateCUDAProviderOptions and
UpdateTensorRTProviderOptions work in the C API, I had assumed that they
updated the options struct, however they re-initialize the struct to the
defaults then only apply the values in the update. I've rewritten the
Java bindings for those classes so that they aggregate all the updates
and apply them in one go. I also updated the C API documentation to note
that these classes have this behaviour. I've not checked if any of the
other providers with an options struct have this behaviour, we only
expose CUDA and TensorRT's options in Java.
There's a small unrelated update to add a private constructor to the
Fp16Conversions classes to remove a documentation warning (they
shouldn't be instantiated anyway as they are utility classes containing
static methods).
### Motivation and Context
Fixes#20544.
### Description
The dml_provider_factory header file can't be used in C programs as it
defines C++ inline operators. This PR rearranges that header file so
that it looks like valid C when used from C, and also makes a couple of
small modifications to the Java code so it correctly binds to the DML EP
at build time.
I'm having some difficulty testing it as I think it's pulling in the old
version of DirectML on my computer and I can't figure out what the
library loading path is in Java to make it look at the recent version I
downloaded. So the test I added fails with:
```
InferenceTest > testDirectML() FAILED
ai.onnxruntime.OrtException: Error code - ORT_RUNTIME_EXCEPTION - message: Exception during initialization: <path-to-ort>\onnxruntime\core\providers\dml\DmlExecutionProvider\src\AbiCustomRegistry.cpp(518)\onnxruntime.dll!00007FFF74819333: (caller: 00007FFF74793509) Exception(3) tid(4f58) 80070057 The parameter is incorrect.
at app//ai.onnxruntime.OrtSession.createSession(Native Method)
at app//ai.onnxruntime.OrtSession.<init>(OrtSession.java:74)
at app//ai.onnxruntime.OrtEnvironment.createSession(OrtEnvironment.java:236)
at app//ai.onnxruntime.OrtEnvironment.createSession(OrtEnvironment.java:221)
at app//ai.onnxruntime.InferenceTest.openSessionSqueezeNet(InferenceTest.java:1961)
at app//ai.onnxruntime.InferenceTest.runProvider(InferenceTest.java:665)
at app//ai.onnxruntime.InferenceTest.testDirectML(InferenceTest.java:657)
```
But it does correctly compile, and this error seems very similar to
other issues with the DML provider when it doesn't like a model due to
the loaded library being old. The test is using the squeezenet file
that's been in the repo since 2019. If someone can help me figure out
how to get the right version of DML in the library path I can test it
more on my end. I tried adding the folder with the new version into the
system path, but I'm not very familiar with Windows' library loading
behaviour.
### Motivation and Context
Fixes#19656 to allow use of the DirectML EP from ORT Java.
cc @martinb35
### Description
Bump spotless and the Gradle wrapper to 6.25.0 and 8.6 respectively to
allow compiling ORT on Java 21. The build still targets Java 8.
I'm not sure if there will be CI changes necessary to use this PR,
specifically for the Gradle version as I don't know if that is cached
somewhere earlier in the CI build process.
The new Gradle version adds a warning that using `--source` and
`--target` to select the Java language version is obsolete which is
annoying, we can fix it if we decide to only allow building on newer
versions of Java, while still supporting running on Java 8.
### Motivation and Context
Java 21 is the latest LTS release of Java and ORT should be able to
build on it.
### Description
Increase the threshold to 1e-5 to avoid test failed in CUDA when
difference is slightly larger than 1e-6.
May because TF32 is used in those CUDA tests.
### Motivation and Context
https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=1291322&view=logs&j=f2f63060-d9d6-52d0-adee-b97db5a9ab91&t=28e21ca6-87a4-5e1e-0441-72b5e8326f2d
ProviderOptionsTest > testCUDAOptions() FAILED
org.opentest4j.AssertionFailedError: array contents differ at index
[103], expected: <0.0102678> but was: <0.010266338>
at
app//org.junit.jupiter.api.AssertionFailureBuilder.build(AssertionFailureBuilder.java:151)
at
app//org.junit.jupiter.api.AssertionFailureBuilder.buildAndThrow(AssertionFailureBuilder.java:132)
at
app//org.junit.jupiter.api.AssertArrayEquals.failArraysNotEqual(AssertArrayEquals.java:440)
at
app//org.junit.jupiter.api.AssertArrayEquals.assertArrayEquals(AssertArrayEquals.java:290)
at
app//org.junit.jupiter.api.AssertArrayEquals.assertArrayEquals(AssertArrayEquals.java:123)
at
app//org.junit.jupiter.api.AssertArrayEquals.assertArrayEquals(AssertArrayEquals.java:119)
at
app//org.junit.jupiter.api.Assertions.assertArrayEquals(Assertions.java:1360)
at
app//ai.onnxruntime.providers.ProviderOptionsTest.runProvider(ProviderOptionsTest.java:99)
at
app//ai.onnxruntime.providers.ProviderOptionsTest.testCUDAOptions(ProviderOptionsTest.java:43)
https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=1293200&view=logs&jobId=f2f63060-d9d6-52d0-adee-b97db5a9ab91&j=f2f63060-d9d6-52d0-adee-b97db5a9ab91&t=28e21ca6-87a4-5e1e-0441-72b5e8326f2d
InferenceTest > testCUDA() FAILED
org.opentest4j.AssertionFailedError: array contents differ at index
[103], expected: <0.0102678> but was: <0.010266337>
at
app//org.junit.jupiter.api.AssertionFailureBuilder.build(AssertionFailureBuilder.java:151)
at
app//org.junit.jupiter.api.AssertionFailureBuilder.buildAndThrow(AssertionFailureBuilder.java:132)
at
app//org.junit.jupiter.api.AssertArrayEquals.failArraysNotEqual(AssertArrayEquals.java:440)
at
app//org.junit.jupiter.api.AssertArrayEquals.assertArrayEquals(AssertArrayEquals.java:290)
at
app//org.junit.jupiter.api.AssertArrayEquals.assertArrayEquals(AssertArrayEquals.java:123)
at
app//org.junit.jupiter.api.AssertArrayEquals.assertArrayEquals(AssertArrayEquals.java:119)
at
app//org.junit.jupiter.api.Assertions.assertArrayEquals(Assertions.java:1360)
at app//ai.onnxruntime.InferenceTest.runProvider(InferenceTest.java:676)
at app//ai.onnxruntime.InferenceTest.testCUDA(InferenceTest.java:615)
### Description
The Java `TensorInfo` object which is used to describe a tensor's shape,
along with the input and output placeholders for a model couldn't show
any symbolic/named dimensions in that tensor. Now this information is
stored in Java strings on construction and included in the toString.
### Motivation and Context
Setting symbolic dimensions required external information in Java, the
names were not discoverable from within the API.
### Description
The `OnnxValue` and `OrtProviderOptions` implementations now check to
see if they've been closed before accessing the native pointer, and also
before close is called.
### Motivation and Context
Before they could be closed twice which SIGSEGV'd the JVM. Fixes#19125.
### Description
Adds a method to access the backing direct byte buffer from a Java
`OnnxTensor` object, assuming it is backed by a direct byte buffer
(tensors created by ORT's run call or ones created in Java from
multidimensional arrays are not). Also adds a method to check if the
backing byte buffer was copied from the user's buffer supplied on
creation (this could be tested via a pointer comparison from the output
of `getBufferRef` and the user's input buffer, so I'm not sure if it's
necessary).
### Motivation and Context
This is the first part of changes necessary to support output pinning in
Java OrtSession.run/OrtTrainingSession.run calls. I split it out from
the rest of the work as it's useful by itself (e.g. to allow users to
keep a single input tensor and rewrite it each time with new inputs
rather than allocate a fresh one) and the other change will be much more
involved so splitting it makes it easier to review.
cc @yuslepukhin
### Description
Reduces precision on the CoreML provider test as it returns slightly
different answers than the other tested providers. Checked on a 2020 13"
M1 MBP.
### Motivation and Context
Fixes Java CoreML test failure after #16763.
### Description
This PR splits out the FP16 conversions into a separate package we can
override in the android build with a version which works on old versions
of Android.
I'm not sure the android build system changes are correct as I haven't
got an android build environment configured on my workstation.
@YUNQIUGUO if the CI build fails we should follow up offline to get my
environment configured so I can iterate on it.
### Motivation and Context
Fixes the CI failure after #16703.
### Description
The Java API currently only supports fp16 output tensors which it
automatically casts to floats on the way out. This PR adds support for
creating fp16 and bf16 tensors (from `java.nio.Buffer` objects or as the
output of models, creation from Java short arrays is not supported),
along with efficient methods for casting `FloatBuffer` into
`ShortBuffer` filled with fp16 or bf16 values and vice versa.
The fp16 conversions use a trick to pull in the efficient conversion
methods added to Java 20, falling back to ports of the MLAS methods
otherwise. The Java 20 methods can be special cased by the C2 JIT
compiler to emit the single instruction on x86 and ARM which converts
fp32<->fp16, or the vectorized versions thereof, so they should be quite
a bit faster than the MLAS ported one.
### Motivation and Context
fp16 and bf16 are increasingly popular formats and we've had several
requests for this functionality. Fixes#7003.
cc @yuslepukhin @cassiebreviu
---------
Co-authored-by: Scott McKay <Scott.McKay@microsoft.com>
### Description
Adds support for adding external initializers or overriding initializers
to a session options from Java.
### Motivation and Context
We want to instantiate large models from Java without filesystem access.
cc @yuslepukhin
🛠️ __Changes in this pull request:__
This pull request introduces two significant changes to the project:
- Changing on device training checkpoint format: The current
implementation stores the on device training checkpoint as a sequence of
tensors in multiple files inside a checkpoint folder, which can be
inefficient in terms of storage and performance. In this PR, I have
modified the checkpoint format to utilize the flatbuffer table to save
the checkpoint to a single file, providing a more compact and efficient
representation. The changes around this are twofold:
- Add the checkpoint flatbuffer schema that will generate the necessary
checkpoint source files.
- Update the checkpoint saving and loading functionality to use the new
format.
- Adding support for onnxruntime minimal build: To support scenarios
where binary size is a constraint, I made changes to ensure that the
training build can work well with the minimal build.
🔍 __Open Issues:__
- In order to extract the optimizer type, the existing implementation
re-loaded the onnx optimizer model and parsed it. This is no longer
possible, since the model format can either be onnx or ort. One idea is
to do the same for ort format optimizer model. This needs some
investigation.
- Changes to the offline tooling to generate ort format training
artifacts.
- End-to-end training example showcasing the use of the minimal training
build.
- Add support for export model for inferencing in a minimal build.
### Description
The name of the flag we set when compiling the JNI binding to enable the CoreML EP changed at some point in the past. This PR fixes it by updating the flag in the JNI. I also added a quick smoke test for the CoreML provider to make sure it doesn't crash and can be enabled.
### Motivation and Context
All the EPs should work as expected in Java. Fixes#16230.
### Description
The tensor creation code now allows the creation of boolean tensors from
non-direct `ByteBuffer` instances. It previously only allowed them from
arrays and direct `ByteBuffer` instances and this fixes that
inconsistency. The boolean tensor test has been updated to cover all
three cases.
### Motivation and Context
Fixes#15509.
### Description
Updating the build option for enabling training in java builds from
ENABLE_TRAINING -> ENABLE_TRAINING_APIS.
In the native codebase ENABLE_TRAINING is used for enabling full
training and ENABLE_TRAINING_APIS is used for creating the lte builds
with training apis. Making the change to sync the naming convention
across all the language bindings.
It was a bit confusing to see ENABLE_TRAINING when debugging the android
build failures for training. Making this change just to improve
readability of logs during debugging.
### 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
Allows the creation of zero length tensors via the buffer path (the
array path with zero length arrays still throws as the validation logic
to check it's not ragged would require more intrusive revision), and
allows the `tensor.getValue()` method to return a Java multidimensional
array with a zero dimension. Also added a test for the creation and
extraction behaviour.
### Motivation and Context
The Python interface can return zero length tensors (e.g. if object
detection doesn't find any objects), and before this PR in Java calling
`tensor.getValue()` throws an exception with a confusing error message.
Fixes#7270 & #15107.
- Update Gradle version used in most places from 6.8.3 to 8.0.1. Update Android Gradle Plugin version where applicable.
Not updated in this change: React Native Android projects (under `js/react_native/`). That can be done later along with updating the React Native projects.
- Add Gradle wrapper in `java/` to make it easier to consistently use a specific Gradle version.
Description
Add bindings for Android and iOS.
Motivation and Context
Enable mobile app linking against ort-extensions library and registering the custom ops with ORT.
**Description**:
Adds support for creating and receiving sparse tensors in the ORT Java
API.
CSRC and COO tensors as inputs are tested, but there is no op which
accepts a block sparse tensor to test. COO tensors are tested as
outputs, but there is no op which emits a CSRC or block sparse tensor to
test.
**Motivation and Context**
- Why is this change required? What problem does it solve? Request to
expose ORT sparse tensor support in Java.
cc @yuslepukhin
Previously OnnxSequence would flatten out a list of tensors into a
single output array assuming they were all scalar values. This doesn't
accurately represent the semantics of an ONNX sequence, but was what the
semantics appeared to be years ago when I first wrote that class. This
PR changes it so that the `getValue` method on `OnnxSequence` unwraps
the sequence and returns `List<? extends OnnxValue>` allowing the user
to process the individual ONNX values separately. It's done this way
rather than returning a multidimensional array for a tensor and a Java
map for a map as multidimensional arrays are very inefficient in Java
and best practice when operating with a OnnxTensor in Java is to use a
`java.nio.ByteBuffer`. So allowing users to access each `OnnxTensor`s
individually allows them to control how the data is materialised on the
Java heap.
# Motivation
Currently, ORT minimal builds use kernel def hashes to map from nodes to
kernels to execute when loading the model. As the kernel def hashes must
be known ahead of time, this works for statically registered kernels.
This works well for the CPU EP.
For this approach to work, the kernel def hashes must also be known at
ORT format model conversion time, which means the EP with statically
registered kernels must also be enabled then. This is not an issue for
the always-available CPU EP. However, we do not want to require that any
EP which statically registers kernels is always available too.
Consequently, we explore another approach to match nodes to kernels that
does not rely on kernel def hashes. An added benefit of this is the
possibility of moving away from kernel def hashes completely, which
would eliminate the maintenance burden of keeping the hashes stable.
# Approach
In a full build, ORT uses some information from the ONNX op schema to
match a node to a kernel. We want to avoid including the ONNX op schema
in a minimal build to reduce binary size. Essentially, we take the
necessary information from the ONNX op schema and make it available in a
minimal build.
We decouple the ONNX op schema from the kernel matching logic. The
kernel matching logic instead relies on per-op information which can
either be obtained from the ONNX op schema or another source.
This per-op information must be available in a minimal build when there
are no ONNX op schemas. We put it in the ORT format model.
Existing uses of kernel def hashes to look up kernels are replaced
with the updated kernel matching logic. We no longer store
kernel def hashes in the ORT format model’s session state and runtime
optimization representations. We no longer keep the logic to
generate and ensure stability of kernel def hashes.
* Specify list/map capacity when initializing where possible
- This really depends on the use case, but in some cases the array/map resizing can be slightly costly, there is effectively no downside setting the initial capacity for a collection if we know for sure its final size
* Supply list/map capacity when initializing where possible
- This really depends on the use case, but in some cases the array/map resizing can be slightly costly, there is effectively no downside setting the initial capacity for a collection if we know for sure its final size
- Introduce an extra utility to help creating maps with expected capacity
* Move utility function to OrtUtil and drop MapUtil, also add Java doc to method
* Move test to the right class
Java side parts for configuring CUDA and TensorRT.
Adding tests for CUDA and TensorRT. Refactoring library loading logic as provider options need to have their shared library loaded before they can be constructed.
