* change BeamSearch op to support encoder decoder model
* check model_type and decoder attribute
* fix
* update comments
* warn shape inference issue with onnx v1.11 or T5
* skip parity test when tempature != 1.0
* fix build
* add support for bool type
* add TVM EP support for tests
* include TVM EP in python test pool
* fix pylint
* moved technical imports to a separate file
* clean up post build actions & move _ld_preload.py extension to CMake level
* add files for include TVM EP into CI
* implement custom logger for TVM
* replace TVM logging with ONNX RT logging
* update link for TVM EP tutorial
* clean up TVM EP cmake
* add pybind auto enabling for TVM EP
* fix blank spaces
* code review fixes
* replace print with comment
* add list of EP without TVM EP
* enable onnx tests
* disable contrib ops and ml ops
* reuse Dockerfile.ubuntu
* Move install_tvm_test_dependencies.sh out of Docker context dir, update build definition.
Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
* Add quantization tool with s8s8 support
* Add unittest for existing s8s8 support operators
* Comment ready unittest for upcomming s8s8 operator (ConvInteger, and Resize)
* Minor change on quantization tools
* Use different s8 min value upon weight or activation.
* use same qmin for reduce ranged s8.
* Add finetuned qdq options
* Add description
* Add unit tests
* Modify for channel axis
* Remove too specific feature. Move this implementation to e2e example
* Add OpTypesSupportPerChannelQuantization
* fix bug for unit test
* Keep flags OpTypesSupportPerChannelQuantization and QDQChannelAxis for internal use
Will have a follow-up PR to fine tune the code
* remove unnecessary warning
Co-authored-by: stevenlix <38092805+stevenlix@users.noreply.github.com>
Co-authored-by: Yufeng Li <liyufeng1987@gmail.com>
* add use_tensorrt build option
* Add use_tensorrt to running tests
* add use_tensorrt for Windows
* make trt ep to skip backend test
* make trt ep to skip backend test
* Fix bug
* Add/Modify description
* modify for debug
* swtich pool to test
* modify to debug
* modify to debug
* add vobersity
* refine the code
* refine the code
* refine the code
* fix flake8 warning
* refine the code
* add pre_load check for trt as well as add cupti lib to cuda depedencies
* modify script to make trt build path the same as cuda
* show error message when user wants to run TensorRT but TensorRT is not installed in the env
* fix bug
* fix bug
* add trt lib for manylinux
* include cuda_dependencies for trt
* rewrite the condition to throw exception
* make code more compact
* remove default python ep registration. raise exception if providers are not explicitly set if there are available providers
* temporarily disable exception
* fix python tests
* explicitly set CUDAProvider for python iobinding tests
* explicitly set providers param for InferenceSession())
* onnxrt
* raise ValueError if not explicitly set providers when creating InferenceSession
* add required providers param
* explicitly set providers
* typo
* Changes to fuse embed layer for gpt2, kernal changes pending
* verified add output and regular add match
* Test added for additional output embedlayernorm, working on CUDA
* Test passing on CPU
* updated convert_to_onnx toll to check parity correctly
* removed some debugs
* couple of TODO left as in optimizer.py
* removed changes to optimizer.py
* fixing build
* fixing build
* updated order of initilization
* added a test case for float16
* updating the docs
* updating tests failing due to embed layer fusion
* update unit tests
* updating CUDA documentation in operatorkernels.md
* addressing comments
* OperatorKernels.md updated with CUDA
* adding TODO to qembed_layer
* minor edit
* updated docs
* addressing comments
* adding position ids to embed layer gpt2
* updating fused gpt2 model
* added extra test
* remove comments
* addressing comments
* contrib_defs.cc updated
* all tests passing
* fixing a typo
* minor edit
* trigger build
* qembedlayernorm checkinputs updated
* fixing build error
* fixing build error
* fixing build error
* add initializer checker for Gather with 1D input
* Check if indices value exists
* Update symbolic_shape_infer.py
* add unit test
* Update symbolic_shape_infer.py
* Update symbolic_shape_infer.py
* implement cuda provider
* define profiler common
* call start after register
* add memcpy event
* add cuda correlation
* format code
* add cupti to test path
* switch to CUpti_ActivityKernel3
* reset cupti path
* fix test case
* fix trt pipeline
* add namespace
* format code
* exclude training from testing
* remove mutex
(1) Attention Fusion for gpt-2 model from Megatron.
(2) Update symbolic shape inference of Attention to support 4D mask.
(3) Add an otpion in save_model_to_file to save external data in one file or not, and warning of existing external data
(4) Fix deprecation: logger.warn => logger.warning
(5) Add model loader to test model without external data
(6) Add an API of optimize_by_fusion, and topological sort after optimization.
* Include pytorch_export_contrib_ops in inference builds
Rename / move it from tools/python/register_custom_ops_pytorch_exporter
to onnxruntime/python/tools/pytorch_export_contrib_ops.
Rationale for inclusion in inference builds:
This code is potentially useful for anyone using ORT, not just training.
Rationale for new name:
"Contrib op" is the nomenclature used within ORT to refer to the set of
ops that are not in the standard op set but are included by default with
ORT. This is more specific than "custom op", which is what the PyTorch
exporter uses to refer to any non-standard op.
Step 1 of addressing #8818. After this is merged I will update the docs.
* Enable test_pytorch_export_contrib_ops.py in CI
Fixes AB#1342330
* support register external ep lib inforation; make eager mode share the same ep pools with training workloads
* fix inference code
* fix build break
* fix the message
Allow FastGelu half2 kernel to build without --cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=xx
Add environment variable ORT_TRANSFORMER_OPTIONS=4 to disable half2 FastGelu kernel for testing purpose
Test parity of FastGelu operator with fp16 inputs.
* rename BertOptimizationOptions to FusionOptions
* remove disable_onnxruntime, and use opt_level to control whether onnxruntime graph optimization is used.
* Change default opt_level for backward compatible. When opt_level is not specified, default value is based on model type.
Re-enable tests that disabled in PR 8530
Update import of test_optimizer.py so that the test could run in source directory.
Add a parameter to disable symbolic shape inference in fp16 conversion since it throws exception for some model.
