* try to run inside 4.3.1 container
* no \ in container run command
* remove networking options
* try with adding video render groups
* add job to build docker image
* try without 1st stage
* change alpha, beta to float
* try adding service connection
* retain huggingface directory
* static video and render gid
* use runtime expression for variables
* install torch-ort
* pin sacrebleu==1.5.1
* update curves for rocm 4.3.1
* try again
* disable determinism and only check tail of loss curve and with a much larger threshold of 0.05
* disable RoBERTa due to high run variablity on ROCm 4.3.1
* put reduction unit tests back in
* initial change for eager/ortmodule integration
* pdate to latest pytorch api
* add test model;fix torch version issue
* fix comments in pr
* fix python test break
* fix api change
* fix comments in PR
* pass device into the fw function
* 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
* draft - enable model local function
* enable model local functions in ORT
* update to latest rel onnx commit
* plus tests
* plus more updates
* plus updates
* test updates
* Fix for nested functions + shape inference
* plus bug fix and updates per review
* plus fixes per review
* plus test updates
* plus updates per review
* plus fixes
* fix a test
* 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
* Use PROTOBUF_LIB instead of protobuf::libprotbuf
* Moved setdlopenflags to _pybind_state.py
* Copy the generated _pybind_state.py to required location for Windows.
* special case concat and split when sizes are equal
* add tests for 16 and 32 inputs with same dim
* add tests for 16/64 inputs on concat or 16/64 outputs on split
* try eliminate windows warning
* outter => outer
* test running hf bert-large
* try again
* try again
* include other models
* correct names
* disable deberta-v2-xxlarge
* avoid torch.distributed
* add compare json loss and perf for bert-large to test
* fix sed expression
* remove pytest
* add more models
* move unit tests u
* display samples/sec
* 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
The following ops have been added to the DNNL execution provider
Abs, Elu, Exp, Log, *Relu, Round, Sigmoid, Softplus, Sqrt, and Tanh
*Relu op was moved from its individual file to the elementwise operators
The error tolerance for the LogGrad unit test had to be decreased slightly
when using OneDNN. Still investigating why a differet tolerance value is
needed.
DnnlSubgraph::AddKernels() member function was moved to the top of the file
since this is eddited every time a new operator is added to the the execution
provider this places the code at the top which mean less scrooling when
adding new kernels.
Signed-off-by: George Nash <george.nash@intel.com>
* Expose symbols in onnx and protobuf namespaces in python when building with --enable_external_custom_op_schemas
* Add external onnx and protobuf files to wheel
* Added an example to demonstrate external custom ops use-case
* Added a Linux build pipeline to test external custom ops
* seperate the training python module; share the execution proivder instance
* fix build break
* fix cuda test crash; reorg the python module code base
* se correct env
* use provider customized hash func
* fixbuild break
* fix rocm break
* use const ref in argument
* rename the file
* move hash func to trainiing module
* Ported changes / bug fixes from torch/ort.
* Fixed formatting
* Renamed function
* Renamed module_ to module.
* Revert "Renamed module_ to module."
This reverts commit b17fc114b3db20d174283811d90592b5b8154c19.
* Include pybind common header to fix linker errors on windows debug.
* Fix to generation of > 1 custom op.
Co-authored-by: Ashwin Hari <ashari@microsoft.com>
* Implement Gemm op for DNNL execution provider
Signed-off-by: George Nash <george.nash@intel.com>
* Remove KernelRegistry and Gemm op for dnnl ep
The KernelRegistry for the dnnl execution provider only
registered a Gemm op that as best we can tell was never
actually used and also was not using the dnnl library.
We have implemented a Gemm op in the DNNL execution provider
subgraph code and thus are removing the unused Gemm op that
was in the dnnl KernelRegistry.
Signed-off-by: George Nash <george.nash@intel.com>
* Fix duplicated output and kernelshape inference
fix getcapability to make sure subgraph outputs do not have duplicates
fix kernelshape inference in pool
Signed-off-by: Wang <zhaoyang.wang@intel.com>
* Removed most dnnl specialized ifdefs from gradient_ops_test code
Re-enable GlobalAveragePoolGrad test for dnnl ep
The bugs that were exposed by the GlobalAveragePoolGrad test have
been fixed and this test no longer needs to be disabled for DNNL.
Removed the ReluGradDnnl test. We are getting the testing from the
already existing ReluGrad test.
MaxPoolGrad test no longer has specialized execution provider
enabling for DNNL execution provider. It will now run without
the extra enabling.
ConvGrad is the only test that still has dnnl specialized ifdefs
However, the ConvGrad code was not being executed by the code
unless it was listed first in the list of execution providers.
Signed-off-by: George Nash <george.nash@intel.com>
* Fix transpose issue on Gemm
On transposing square matrices, getmemoryandreshape will fail to reshape
fix by adding a bool
Signed-off-by: Wang <zhaoyang.wang@intel.com>
* Save memory space by reusing internal tensor for output
The intermediat matmul output tensor can be used as the output
tensor for the binary calculation.
Remove the unused IsAttributeSupported from the
DnnlGemmNodeCapability class since we now support all of the
Gemm attributes in our implementation.
Signed-off-by: George Nash <george.nash@intel.com>
Co-authored-by: Wang <zhaoyang.wang@intel.com>
* adding support for tracing to sqldb instead of files
* use compiled statements
* script to pull tensors from db
* link sqlite3
* remove node info redundant with onnx graph
* addressing PR comments
* address PR comments and include program counter
* third party notice
* use find_pacakge
* add to cgmanifests.json
* address thread safety and add pid suffix
* build fi
* python script to select on devicetype
* remove unpopulated and redundant Shape and Type fields
* comment
* comment
* PR comments
* add graph execution counter to session state
* move increment to inference session
* std::endl to \n
* ifdef on graph execution counter
* add ifdef to inference session
* move DEBUG_NODE_INPUTS_OUTPUTS to CMakeLists.txt
* Fetching frontier tensors to frontend
* Move before session initialize call
* Fetch tensor and add to cache
* Rest of the changes for using cache
* Review comments
* Review changes
* Review comments
* switch to shared_ptr
* Fix bug after rebase
* FE docstring change
