* changes
* tile grad unsqueeze fix for opset 13
* clean up
* remove bool support for opset 2 to 12 for Pad as it is not supported.
* Copy OperatorKernels.md from artifacts of Windows CI build.
* updates for picking pnnx commit
* add tests filter to c# tests
* plus test fixes
* fix versioning for contrib ops
* fix tests
* test filter for optional ops
* more versioning related updates
* fix test
* fix layernorm spec
* more updates
* update docs
* add more test filters
* more filters
* update binary size threshold
* update docs
* plus more fixes
* updates per review
* update to release commit
* add filters for optional type tests
* plus updates
QGemm takes in quantized A, B, C, and quantization parameters of output Y, in which C and quantization parameters of Y are optional. Its output can be quantized or full precision, which depends on whether quantization parameters of Y exists or not. If quant params of Y are provided, the output will be requantized or is full precision.
Comparing with QLinearMatMul and MatMulInteger, QGemm supports transpose, apha and beta attribute.
The formula for quantized GEMM is:
Y = alpha * scale_a * scale_b * ((A_int8 - zp_a) * (B_int8 - zp_b) + C_int32), in which,
C_int32 is quantized with formula: C_int32 = (beta * C) / (alpha * scale_a * scale_b)
SparseTensor support
Implement Builder pattern
Fix support for 1-D and 2-D COO indices
Implement and test CSR support.
Handle shape inference for SparseTensors
Implement conversion for COO, CSR and tests.
Address the case where constant sparse initializer is the output.
Implement test infra for SparseTensors
Implement SparseDenseMatMul for Csr and COO and tested it.
Add hash for SparseToDenseMatMul
Finish shared provider refactor
Refactor GetOrCreate to Create
Working on py interface
Expose OrtDevice and use it in allocate_numpy
Adjust Sparse interfaces, add support for string SparseTensor. Add tests.
Add and test to_cuda()
Add accessors to format specific indices
Test values and indices views, read-only flag, after GC access
Add sparse related methods to OrtValue
Re-work SparseTensor wrapper, add OrtValue methods
Rework numpy_array_to_cuda/to_cpu
Add run_with_ort_values
Add models and test sparse_mat_mul with run_with_ort_values
Refactor sparse tensor to use a single buffer
Ifdef x86 Eigen CSR sparse matmul implementation
Exclude broken test, check for string type when copying cross device
Split pybind schema, regenerate docs, add exclusion
Conditionally exclude schema module
Update docs fix cuda build
Add test to a filter and renerate JS docs
Add conversion and test string support for sparse tensors
Exclude conversion utils from minimal build
Add CUDA Memcpy and adjust provider interfaces
* add Gridsampler contrib op
* fix gridsampler_paddingmode_border test
* disable the tests until the kernel added
* fix CI failure
* change GridSampler to GridSample
* changes working to convert akv nodes
* changes to replace nodes
* changes to accomodate qkv hidden sizes as attributes
* kernel to accept qkv_hidden_size attributes
* Working till compute for varied dimension, todo applyattention()
* changes to make all regression tests work
* inference running successfully without prepack
* success inference with pre-pack weights
* add test for diff sizes
* bias shape need not be a mul of 3
* get the output_hidden_size from input
* infer output shape from input
* merge with master
* cleaning up files that got merged wrong
* accurancy at accepted level
* added unit test case for different dimensions
* all unit tests passing
* packed weights working for attention
* prepacked weights working
* added test case for newly added extra qk input
* updated unit test to test only extra add qk
* fixing build error
* removing few debugs
* reverting test changes
* all python test passing
* cleaning up
* new unit test added, major clean up of code
* removed extra code
* minor
* minor fix to tests
* prepack weights code cleaned up
* compacted compute() in attention.cc
* reformat compute()
* making a parameter T
* adding 3 q,k,v buffers in all cases
* fixing build
* running tests only on cpu
* Updating docs
* trigger ci builds
* Addressing comments in PR
* addressing some more comments
* get add_qk_str from add_qk node directly
* updating docs, added extra check to verify attn inputs
* Optimized the extra add by parallelizing
* added attention_shape to symbolic_shape_infer.py
* minor refactoring to address comments
* Update submodule onnxruntime-extensions to latest.
* Add document for onnxruntime-extensions.
* Update cgmanifest.json for onnxruntime-extensions.
* Add example in JavaScript.
Co-authored-by: Zuwei Zhao <zuzhao@microsoft.com>
**Description**:
Enforce no repetition of n-grams. Scores are set to `-inf` for tokens that form a repeated n-gram if added to the back of the input_ids.
**Motivation and Context**
Needed by transformer models in sequence generation algorithms (greedy search and beam search). This module has heavy impact on performance, and can be highly parallelized.
* Update the operator documentation generation
- Make layout a little nicer
- Update to latest supported operators including training
- Fix some links that are broken when the docs content is copied to github-pages
- Fix incorrect usage of 'onnx.ai.ml' as the default domain
- ML ops are now separated from the real default domain of 'onnx.ai'
- Include CPU, CUDA and training kernels
- exclude DNNL as it's not an EP we own
* There are separate paths for CUDA and CUDNN as they are not guaranteed to be in the same location on a Windows machine. Use the CUDNN path when looking for the CUDNN library.
* Enable validation of both contrib ops and operator kernels in build
Filter generation so it's deterministic
Add ability for CI to publish the md files as build artifacts if they differ so a developer can download and add to their PR to resolve any diffs.
Remove workarounds for github-pages as that will now link to the github docs which display correctly
* checkin
* add 4dmask support in attention cuda op
* trim
* add comments
* fix build/test error
* review comments and add tests
* sync doc
* review comments
* minor change
* Include ORT format model conversion scripts and infrastructure in ORT python package.
- tweak existing script setup so it can be easily run directly and from the ORT python package
Add config file and readme for Android minimal build package
Update ORT Mobile doco
Disable warning if 'all' optimizations are enabled but NCHWc transformer is excluded (device specific optimizations don't apply in this scenario so the warning is moot).
* Address PR comments
Implement various improvements related to reordering a tensor for use by NCHWc operations:
Relax the requirement that the input channel count must be a multiple of the NCHWc block size (either 8 or 16 depending on ISA). The requirement now is that the channel count must be a multiple of 4. The implementation of MlasReorderInputNchw would need further work to support relaxing this further, but I don't have any models where I've observed this to be necessary yet.
Support fusing a Transpose(NHWC->NCHW) into a following ReorderInput. ReorderInput now has a channels_last attribute as was done in the past for ReorderOutput. This helps with models converted from TF where the converter is unable to remove all Transpose operations.
Add threading support to ReorderInput to accelerate performance (ReorderOutput will come later).
* Implement qlinear concat and unit test.
Add quantization tools for QLinearConcat and it quantization tests.
* Add kernel def hash for QLinearConcat.
* Change according to PR. Add qdq transformer support for QLinearConcat.
* Add QDQ Transformer unittest. Fix typo on domain.
* remove dup logic of no use.
* fix x86 build error.
* Update operator docs.
* Add support for custom ops library to the ORT model conversion script
Simplify model conversion now that we read ops from the ORT format model.
Enable custom ops in the python bindings if custom ops are turned on in a minimal build.
* Add test of model conversion involving custom ops.
* Add ability to generate configuration that includes required types for individual operators, to allow build size reduction based on that.
- Add python bindings for ORT format models
- Add script to update bindings and help info
- Add parsing of ORT format models
- Add ability to enable type reduction to config generation
- Update build.py to only allow operator/type reduction via config
- simpler to require config to be generated first
- can't mix a type aware (ORT format model only) and non-type aware config as that may result in insufficient types being enabled
- Add script to create reduced build config
- Update CIs
Update Python API to allow more flexibility for setting providers and provider options.
The providers argument (InferenceSession/TrainingSession constructors, InferenceSession.set_providers()) now also accepts a tuple of (name, options dict).
Fix get_available_providers() API (and the corresponding function in the C API) to return the providers in default priority order. Now it can be used as a starting point for the providers argument and maintain the default priority order.
Convert some usages of the deprecated global configuration functions to use EP-specific options instead.
Update some EP-specific option parsing to fail on unknown options.
Other clean up.
* Enabling fasterrcnn variant and vehicle detector
* changes for 2021_2 branch
* yolov3_pytorch commit
* fixed braces in basic_backend.cc
* ci information added
* faster rcnn variant and vehicle detector changes were made in 2021.1 and not in 2021.2
* some changes to support unit tests
* disable some tests which are failing
* fix myriad tests for vehicle detector
* Did some cleanup
*cleaned up comments
*Disabled Add_Broadcast_0x1 and Add_Broadcast_1x0
tests on MYRIAD_FP16 backend due to a bug
*cleaned up capability_2021_2.cc file
*Removed extra conditions which were added
for some validation in backend_utils
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* yolov3 pytorch workaround to ensure that the output names are matched
* gemmoptest fixed on myriad
* Fixed MYRIADX CPP Test Failures
*Expand,GatherND,Range,Round op's
are only supported in model
*where op with float input data
types are not supported and fixed
*Scatter and ScatterElements op's with
negative axis are fixed
*Reshape op with 0 dim value are not
supported and fixed
*Disabled InstanceNorm_2 test on MYRIADX
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* make changes to yolov3 pytorch
* Fixed python unit tests
*Fixed failing python tests on vpu,
GPU and CPU
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Fixes POW op failures on GPU_FP16
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Clean up capability_2021_2.cc
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Updated docx for MultiThreading option
*Added extra info on setting the num_of_threads
option using the API and it's actual usage
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* fixed slice and removed extra prints
* Disabled failing python tests
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Minor changes added in capabilty_2021_2
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* made changes to slice to avoid failures
* Disabling FP16 support for GPU_FP32
->Inferencing an FP16 model on GPU_FP32
leads to accuracy mismatches. so, we would
rather use GPU_FP16 to infer an FP16 model
on GPU Device
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Updated docx for Inferencing a FP16 Model
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* fix for mask rcnn
* Script for installing openvino from source
* Updated with openvino 2021.2 online installation
* code comment fixes
fixed accuracy mismatch for div
* Update OpenvinoEP-ExecutionProvider.md
updated for 2021.2 branch
* Update README.md
updated dockerfile documentation
* Update BUILD.md
build.md update documentation
* permissiong change of install_openvino.sh
* made changes to align with microsoft onnxruntime changes
* Updated with ov 2021.2.200
Co-authored-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
Co-authored-by: sfatimar <sahar.fatima@intel/com>
Co-authored-by: MaajidKhan <n.maajidkhan@gmail.com>
Co-authored-by: mohdansx <mohdx.ansari@intel.com>
* allow custom op taking varied types
* refactor test case
* add test model
* refactor test case
* enable copy elision
* update test case
* fix issue in ToString function
* Update version to 1.6.0
* Add v 1.5.3 info
* Updating WindowsAI and ONNX version
Co-authored-by: Du Li <duli@OrtTrainingDev0.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net>
* Expand the documentation on using compiling EPs with a minimal build to call out a 'simple' option that is easier to use. Provide more background on what happens to help users choose the best option for them.
Tweak conversion script to be noisier about attempted usage of 'all' optimization level.
Co-authored-by: manashgoswami <magoswam@microsoft.com>
* Update OpenVINO-ExecutionProvider.Md
update openvino-executionprovider.md for shared library
* Update Build.md
updated --build_shared_lib flag for building openvino shared provider lib
* Update Dockerfile.openvino
building for shared library with the new changes for openvino shared lib
* Revert "Update Build.md"
This reverts commit c9cf5fee76be7fdc10cadf07259f1d4ed5b45b93.
* Revert "Update Dockerfile.openvino "
This reverts commit e1624e4f93a4cfb425b6f21d7fb71b299a146740.
* Update OpenVINO-ExecutionProvider.md
fix documentation to the shared library
Co-authored-by: sfatimar <sahar.fatima@intel/com>
* Add initial documentation on using NNAPI with a minimal build
* minor clarification
* Add note on avoiding local full build
* Address a couple of PR comments
* add int8
* support both native TRT cal table and ORT cal table
* add more comments
* Update env variable name and check platform availability for int8/fp16
* add backward compatibility on old env var ORT_TENSORRT_ENGINE_CACHE_PATH and switch to flatbuffers for ort cal table deserialization
* add int8
* support both native TRT cal table and ORT cal table
* add more comments
* Update env variable name and check platform availability for int8/fp16
* Remove nGraph Execution Provider
Pursuant to nGraph deprecation notice: https://github.com/microsoft/onnxruntime/blob/master/docs/execution_providers/nGraph-ExecutionProvider.md#deprecation-notice
**Deprecation Notice**
| | |
| --- | --- |
| Deprecation Begins | June 1, 2020 |
| Removal Date | December 1, 2020 |
Starting with the OpenVINO™ toolkit 2020.2 release, all of the features
previously available through nGraph have been merged into the OpenVINO™
toolkit. As a result, all the features previously available through
ONNX RT Execution Provider for nGraph have been merged with ONNX RT
Execution Provider for OpenVINO™ toolkit.
Therefore, ONNX RT Execution Provider for **nGraph** will be deprecated
starting June 1, 2020 and will be completely removed on December 1,
2020. Users are recommended to migrate to the ONNX RT Execution Provider
for OpenVINO™ toolkit as the unified solution for all AI inferencing on
Intel® hardware.
* Remove nGraph Licence info from ThirdPartyNotices.txt
* Use simple Test.Run() for tests without EP exclusions
To be consistent with rest of test code.
* Remove nGraph EP functions from Java code
Transitions from the ORT-only DML NuGet (hosted on the onnxruntime_public feed) to the new unified DirectML NuGet (Microsoft.AI.DirectML) on nuget.org. In addition, the Microsoft.AI.MachineLearning (WinML) and Microsoft.ML.OnnxRuntime.DirectML packages now take a dependency on the Microsoft.AI.DirectML package. This means we can remove the extra copy of DML binaries in these packages since they will be installed by the DML package.
* add case for cpu custom op on gpu
* format doc
* restrict GPU custom op on Linux GPU CI only
* separate cu file to a independent project
* fix typo
* include cuda_add lib
* move lib def
* add file header
Co-authored-by: RandySheriffH <rashuai@microsoft.com>
* add profile caching to improve engine caching feature
* Add comments
* fix typo
* add decryption for engine caching
* Update tensorrt_execution_provider.cc
* Update tensorrt_execution_provider.cc
* Update tensorrt_execution_provider.cc
* Update tensorrt_execution_provider.cc
* Update tensorrt_execution_provider.cc
* update onnx-tensorrt submodule
* set opt profile to max value of the range
* add hash to engine/profile name
* Add calibration based INT8 quantization
* add an option to enable both FP16 and INT8
* Update tensorrt_execution_provider.cc
* add env variable to specify calibration file name
* clean up code
* Add comments and update TRT document
* enable tensorrt basic test and add EngineCachingTest
* clean up
* update envrionment variable in the test
* clean up
* Enabling Multi Device support for UEP
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Minor fix added
*Added a simple fix to determine OpenVINO
version for Arm build as well
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
This PR updates the ThreadPool API to support multi-loop parallel sections. As with the OpenMP "parallel" construct, this allows per-loop work to be amortized over a series of loops. For ORT, it also promotes locality between successive loops in the sense that iteration X of one loop will tend to run on the same worker thread as iteration X of preceding loops.
The change was developed while optimizing the implementation of a model that performed better with OpenMP. Profiling indicated that OpenMP was providing lower loop entry/exit costs and that, via OpenMP's static scheduling, it was leading to a lower L2 miss rate in the series of parallel loops used in GRU.
The main changes are:
- Addition of ThreadPool::ParallelSection and underlying support in the modified Eigen thread pool.
- In EigenNonBlockingThreadPool.h, refactoring the RunInParallel method to support two variants: one that takes an existing parallel section object created by the caller, and another (used by default) that creates its own parallel section.
- Simplify ThreadPool::LoopCounter (used by worker threads to claim loop iterations), basing it an ID supplied by the underlying Eigen thread pool for affinity in a series of loops.
- Fix a possible perf issue where a loop with iterations scheduled in batches would have more threads than batches available.
- Use of parallel sections in the GRU operator.
- Additional test cases in threadpool_test.h.
- Additional comments at the top of threadpool.h and EigenNonBlockingThreadPool.h.
* Implement Hetero in UEP
* Added security checks to take valid Hetero combinations
as device type
* Integrating Hetero features
* Get the statistics Report in Debug Mode
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Passing right device type for vadm_baackend
Added simple fix to pick the right device type
when using vadm_backend with Hetero as well.
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Fixed batching logic for 2020.4 and above
* Fixed flake8 PEP8 errors
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Minor Fixes Added
*Added security checks for device_type passed
in for Hetero build during run time
*code cleanup
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Minor changes Added
*Fixed batch_size bug in vadm_backend
*code cleanup
*Documentation updated for Hetero
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
Co-authored-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
* add case for cpu custom op on gpu
* format doc
* restrict GPU custom op on Linux GPU CI only
* separate cu file to a independent project
* fix typo
Co-authored-by: RandySheriffH <rashuai@microsoft.com>
Description: This change makes three changes to the ThreadPool class to clean up issues identified during performance analysis and optimization. (1) It uses mm_pause intrinsics in spin loops, helping avoid consuming pipeline resources while waiting. (2) It re-organizes the spin-then-steal loop for work distribution to start out spinning as intended, rather than to start out trying to steal. (3) It updates the ThreadPool class's API to be consistent in the use of static methods for public functions. The PR includes minor doc updates and corresponding changes to test cases.
Motivation and Context
The change helps ensure consistency in behavior between the OpenMP and Eigen-based implementations. Unlike the instance methods, the static methods abstract over the different ways in which threading can be implemented; they will map onto the OpenMP or Eigen-based implementations when threading is used. When threading is not used they will run work sequentially.
* Enabled multi-threading for OpenVino EP
->Enabled support for concurrent_session_runs
*Run UEP using concurrent_session_runs > 1
*Enabled support for ORT_PARALLEL ExecutionMode
->Documentation Added for Enabling MultiThreading
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Minor Fixes added
*Configure the value of nireq during Runtime
*Documentation typos rectified and details
added for Multi_Threaded Inference
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Some checks added for this fix
*Added checks to invalidate wrong nireq value
and assigned it to default value of 8
*Added new config options for enable_vpu_fast_compile
which were changed w.r.t OpenVINO_2021.1 Release
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* updating examples with current api calls
* Fixing capitalization in api calls, adding RKNPU update
* Correcting nuphar and rknpu ep api calls
* Include creating session in readme
* Cmake changes for 2021.1
* added new ov version 2020.1 for faster rcnn
* Added missing defs
* equal op modified
* changes to incoroporate faster rcnn
* backend util.cc
* hddl_plugin_config.hpp is depreceated . instead use hddl_config.hpp
* changing myriad precision bool to i32
* gather is not enabled for gpu
* conv2D and pooltest auto_pad attribute should not be null
* negative indices are not valid for scatter op in myriad
* non max suppression op only supported in faster rcnn mode
* maxpool indices output is not supported
* Cleaned redundant code in backends
* Added ifdefs for HDDL config
* cast output dimensions check
topk operator k input it seems only resolved for myriad as it is
throwing issues for ask rcnn . need to verify
* we are limiting the subgraph size to 3 here
* taking care of review comments
* Fixed minor bugs
* Modified Slice op checks
* Added NonZero, Upsample
* Removed TopK if it's in the middle of a subgraph
* incorporated upsample conditions too
* Dockerfile changes for 2021.1 release
* dockerfile aptkey update
* Minor fixes
* ceil condition added again
* Fixed few gpu models
* Disabled LSTM and yolov3 in ModelTests
* python softmax cross entropy tests and negative log likelihood
* Update Build.md
Updated for openvino 2021.1
* Update OpenVINO-ExecutionProvider.md
update openvino execution provider for 2021.1
* Update READMe.md
updated new openvino version
* Update Dockerfile.openvino
added environment variable for DEBIAN Frontend
* Fixed myriad models
* Fixed gather condition
* Fixed mask rcnn model on myriad
* Modified Gather condition
* set default target of MCR dockerfile to MYRIAD_FP16
* Fixed tinyolov3 on CPU
* Update OpenVINO-ExecutionProvider.md
update openvino execution provider documentation
* Update Dockerfile.openvino
Removed environment variable
* Update OpenVINO-ExecutionProvider.md
update image manipulation networks supported
* Update onnx_backend_test_series_filters.jsonc
removed test_upsample_nearest from cpu test cases
* New InternalCI changes for 2021.1
* Full protobuf removed for OpenVINO
* Protobuf added
* Updated with apt installation for openvino
* Revert the testing changes
* Reverted testing changes
* File permessions are changed to original
* Deleted openvino installation and cmake change
* Optimized Dockerfile
Removed unnecessary cmake installation, numpy
* Added missing ifdefs
* delete array fix
* backend_utils.cc output_shape
* Revert "set default target of MCR dockerfile to MYRIAD_FP16"
This reverts commit 928d3e2b71e2f589cf51dacd3a133951cf9ca18d.
Co-authored-by: suryasidd <surya.siddharth.pemmaraju@intel.com>
Co-authored-by: sfatimar <sahar.fatima@intel/com>
Co-authored-by: suryasidd <48925384+suryasidd@users.noreply.github.com>
Co-authored-by: S. Manohar Karlapalem <manohar.karlapalem@intel.com>
Co-authored-by: Aravind <aravindx.gunda@intel.com>
Co-authored-by: Aravind Gunda <38353114+gundaarx@users.noreply.github.com>
* Fix Windows AI version
* Update text to extend telemetry coverage
Includes all official binaries
* Update text about EP pluggability
* Update CUDA/cuDNN versions
* Add link to reduce operator kernel page
* Update roadmap
* Add preview for migraphx
* Move Rockchip under IoT/Edge
* Update text to include ORT for Mobile doc link
