saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-14 20:48:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/docs/How_To_Update_ONNX_Dev_Notes.md

52 lines
3.5 KiB
Markdown
Raw Normal View History

Support per-test tolerances for ONNX tests (#11775) Prior to this every test shared the same tolerances. This meant that if an ONNX test failed due to a small but acceptable difference in output, the only alternative was to disable the test entirely. In op set 17, the DFT operator is being added. Without this change, the tests for that operator fail because the output is off by about 5e-5. It's better to keep test coverage for this new op rather than disable the test entirely. Also prior to this change, the global tolerances were not shared between C++, JavaScript, and Python tests. Now they are. Also fix various minor issues raised by linters. Unblocks https://github.com/microsoft/onnxruntime/issues/11640.
2022-06-14 22:12:23 +00:00
# How to update ONNX
Add dev notes
2019-02-01 22:16:30 +00:00
Support per-test tolerances for ONNX tests (#11775) Prior to this every test shared the same tolerances. This meant that if an ONNX test failed due to a small but acceptable difference in output, the only alternative was to disable the test entirely. In op set 17, the DFT operator is being added. Without this change, the tests for that operator fail because the output is off by about 5e-5. It's better to keep test coverage for this new op rather than disable the test entirely. Also prior to this change, the global tolerances were not shared between C++, JavaScript, and Python tests. Now they are. Also fix various minor issues raised by linters. Unblocks https://github.com/microsoft/onnxruntime/issues/11640.
2022-06-14 22:12:23 +00:00
This note is only for ONNX Runtime developers.
Add dev notes
2019-02-01 22:16:30 +00:00
Support per-test tolerances for ONNX tests (#11775) Prior to this every test shared the same tolerances. This meant that if an ONNX test failed due to a small but acceptable difference in output, the only alternative was to disable the test entirely. In op set 17, the DFT operator is being added. Without this change, the tests for that operator fail because the output is off by about 5e-5. It's better to keep test coverage for this new op rather than disable the test entirely. Also prior to this change, the global tolerances were not shared between C++, JavaScript, and Python tests. Now they are. Also fix various minor issues raised by linters. Unblocks https://github.com/microsoft/onnxruntime/issues/11640.
2022-06-14 22:12:23 +00:00
If you need to update the ONNX submodule to a different version, follow the steps below.
1. Update the ONNX submodule
```sh
Add dev notes
2019-02-01 22:16:30 +00:00
cd cmake/external/onnx
git remote update
git reset --hard <commit_id>
cd ..
git add onnx
```
(Change the <commit_id> to yours. If you are not sure, use 'origin/master'. Like 'git reset --hard origin/master')
Fix C# and numbering (#11643) * C# protocol buffer code can be updated on Linux. Link to the relevant instructions. * Fix numbering.
2022-05-31 18:33:36 +00:00
1. Update [cgmanifests/generated/cgmanifest.json](/cgmanifests/generated/cgmanifest.json).
CGManifest - add training entries and generate entries for submodules. (#3933) Add cgmanifest.json entries for training dependencies. Add script to generate git submodule cgmanifest.json entries.
2020-05-15 20:34:18 +00:00
This file should be generated. See [cgmanifests/README](/cgmanifests/README.md) for instructions.
Add dev notes
2019-02-01 22:16:30 +00:00
Integration with ONNX 1.16.0 (#19745) ### Description update with ONNX 1.16.0 branch according to https://github.com/microsoft/onnxruntime/blob/main/docs/How_To_Update_ONNX_Dev_Notes.md ONNX 1.16.0 release notes: https://github.com/onnx/onnx/releases/tag/v1.16.0 #### Updated ops for CPU EP: - DequantizeLinear(21) - Added int16 and uint16 support + various optimizer tests - Missing int4 and uint4 support - Missing block dequantization support - QuantizeLinear(21) - Added int16 and uint16 support + various optimizer tests - Missing int4 and uint4 support - Missing block quantization support - Cast(21) - Missing int4 and uint4 support - CastLike(21) - Missing int4 and uint4 support - ConstantOfShape(21) - Missing int4 and uint4 support - Identity(21) - Missing int4 and uint4 support - If(21) - Missing int4 and uint4 support - Loop(21) - Missing int4 and uint4 support - Reshape(21) - Missing int4 and uint4 support - Scan(21) - Missing int4 and uint4 support - Shape(21) - Missing int4 and uint4 support - Size(21) - Missing int4 and uint4 support - Flatten(21) - Missing float8e4m3fnuz, float8e5m2, float8e5m2fnuz, int4, and uint4 support - Pad(21) - Missing float8e4m3fnuz, float8e5m2, float8e5m2fnuz, int4, and uint4 support - Squeeze(21) - Missing float8e4m3fnuz, float8e5m2, float8e5m2fnuz, int4, and uint4 support - Transpose(21) - Missing float8e4m3fnuz, float8e5m2, float8e5m2fnuz, int4, and uint4 support - Unsqueeze(21) - Missing float8e4m3fnuz, float8e5m2, float8e5m2fnuz, int4, and uint4 support #### Unimplemented opset 21 features/ops - int4 and uint4 data type - QLinearMatMul(21) - GroupNormalization(21) - ai.onnx.ml.TreeEnsemble(5) ### 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. --> ### Disabled tests #### ORT Training orttraining/orttraining/test/python/orttraining_test_ort_apis_py_bindings.py - test_ort_custom_ops: Potential shape inference bug for custom ops #### Python quantization unit tests test/onnx/python/quantization (shape inference bug) - test_op_conv_transpose.py: test_quantize_conv_transpose_u8u8_fp16 - test_op_conv_transpose.py: test_quantize_conv_transpose_s8s8_fp16 - test_op_gemm.py: test_quantize_qop_gemm_s8s8 - test_op_gemm.py: test_quantize_qop_gemm_e4m3fn_same - test_op_gemm.py: test_quantize_qop_gemm_e4m3fn_p3 - test_op_matmul.py: test_quantize_matmul_u8u8_f16 - test_op_matmul.py: test_quantize_matmul_s8s8_f16 - test_op_matmul.py: test_quantize_matmul_s8s8_f16_entropy - test_op_matmul.py: test_quantize_matmul_s8s8_f16_percentile - test_op_matmul.py: test_quantize_matmul_s8s8_f16_distribution - test_op_relu.py: test_quantize_qop_relu_s8s8 #### ONNX tests - test_maxpool_2d_ceil_output_size_reduce_by_one: ONNX 1.16.0 fixed a maxpool output size bug and added this test. Enable this test when [ORT PR](https://github.com/microsoft/onnxruntime/pull/18377) is merged. Refer to original [ONNX PR](https://github.com/onnx/onnx/pull/5741). - test_ai_onnx_ml_tree_ensemble_set_membership_cpu: new unimplemented op ai.onnx.ml.TreeEnsemble - test_ai_onnx_ml_tree_ensemble_single_tree_cpu: same - test_ai_onnx_ml_tree_ensemble_set_membership_cuda: same - test_ai_onnx_ml_tree_ensemble_single_tree_cuda: same - test_cast_INT4_to_FLOAT_cpu: ORT Cast(21) impl doesn't support int4 yet - test_cast_INT4_to_INT8_cpu: same - test_cast_UINT4_to_FLOAT_cpu: same - test_cast_UINT4_to_UINT8_cpu: same - test_cast_INT4_to_FLOAT_cuda - test_cast_INT4_to_INT8_cuda - test_cast_UINT4_to_FLOAT_cuda - test_cast_UINT4_to_UINT8_cuda - test_constantofshape_float_ones_cuda: ConstantOfShape(21) not implemented for cuda - test_constantofshape_int_shape_zero_cuda: same - test_constantofshape_int_zeros_cuda: same - test_flatten_axis0_cuda: Flatten(21) not implemented for cuda - test_flatten_axis1_cuda: same - test_flatten_axis2_cuda: same - test_flatten_axis3_cuda: same - test_flatten_default_axis_cuda: same - test_flatten_negative_axis1_cuda: same - test_flatten_negative_axis2_cuda: same - test_flatten_negative_axis3_cuda: same - test_flatten_negative_axis4_cuda: same - test_qlinearmatmul_2D_int8_float16_cpu: QLinearMatMul(21) for onnx not implemented in ORT yet - test_qlinearmatmul_2D_int8_float32_cpu: same - test_qlinearmatmul_2D_uint8_float16_cpu: same - test_qlinearmatmul_2D_uint8_float32_cpu: same - test_qlinearmatmul_3D_int8_float16_cpu: same - test_qlinearmatmul_3D_int8_float32_cpu: same - test_qlinearmatmul_3D_uint8_float16_cpu: same - test_qlinearmatmul_3D_uint8_float32_cpu: same - test_qlinearmatmul_2D_int8_float16_cuda: same - test_qlinearmatmul_2D_int8_float32_cuda: same - test_qlinearmatmul_2D_uint8_float16_cuda: same - test_qlinearmatmul_2D_uint8_float32_cuda: same - test_qlinearmatmul_3D_int8_float16_cuda: same - test_qlinearmatmul_3D_int8_float32_cuda: same - test_qlinearmatmul_3D_uint8_float16_cuda: same - test_qlinearmatmul_3D_uint8_float32_cuda: same - test_size_cuda: Size(21) not implemented for cuda - test_size_example_cuda: same - test_dequantizelinear_blocked: Missing implementation for block dequant for DequantizeLinear(21) - test_quantizelinear_blocked_asymmetric: Missing implementation for block quant for QuantizeLinear(21) - test_quantizelinear_blocked_symmetric: Missing implementation for block quant for QuantizeLinear(21) --------- Signed-off-by: liqunfu <liqun.fu@microsoft.com> Signed-off-by: Ganesan Ramalingam <grama@microsoft.com> Co-authored-by: Ganesan Ramalingam <grama@microsoft.com> Co-authored-by: George Wu <jywu@microsoft.com> Co-authored-by: adrianlizarraga <adlizarraga@microsoft.com>
2024-04-12 16:46:49 +00:00
1. Update Python requirements files with the updated ONNX version (e.g., `onnx==1.16.0`) or commit hash if building from source (e.g., `git+http://github.com/onnx/onnx.git@targetonnxcommithash#egg=onnx`).
- [onnxruntime/test/python/requirements.txt](/onnxruntime/test/python/requirements.txt)
- [tools/ci_build/github/linux/docker/scripts/requirements.txt](/tools/ci_build/github/linux/docker/scripts/requirements.txt)
- [tools/ci_build/github/linux/docker/scripts/manylinux/requirements.txt](/tools/ci_build/github/linux/docker/scripts/manylinux/requirements.txt)
fix requirements.txt path (#22946) ### Description #22380 removes the file `tools/ci_build/github/linux/docker/inference/x86_64/python/cpu/scripts/requirements.txt` but it is still used in `dockerfiles/Dockerfile.cuda`. This change updates the file path of the requirements.txt fixes #22945.
2024-12-04 21:08:29 +00:00
- [tools/ci_build/github/linux/python/requirements.txt](/tools/ci_build/github/linux/python/requirements.txt)
Integration with ONNX 1.16.0 (#19745) ### Description update with ONNX 1.16.0 branch according to https://github.com/microsoft/onnxruntime/blob/main/docs/How_To_Update_ONNX_Dev_Notes.md ONNX 1.16.0 release notes: https://github.com/onnx/onnx/releases/tag/v1.16.0 #### Updated ops for CPU EP: - DequantizeLinear(21) - Added int16 and uint16 support + various optimizer tests - Missing int4 and uint4 support - Missing block dequantization support - QuantizeLinear(21) - Added int16 and uint16 support + various optimizer tests - Missing int4 and uint4 support - Missing block quantization support - Cast(21) - Missing int4 and uint4 support - CastLike(21) - Missing int4 and uint4 support - ConstantOfShape(21) - Missing int4 and uint4 support - Identity(21) - Missing int4 and uint4 support - If(21) - Missing int4 and uint4 support - Loop(21) - Missing int4 and uint4 support - Reshape(21) - Missing int4 and uint4 support - Scan(21) - Missing int4 and uint4 support - Shape(21) - Missing int4 and uint4 support - Size(21) - Missing int4 and uint4 support - Flatten(21) - Missing float8e4m3fnuz, float8e5m2, float8e5m2fnuz, int4, and uint4 support - Pad(21) - Missing float8e4m3fnuz, float8e5m2, float8e5m2fnuz, int4, and uint4 support - Squeeze(21) - Missing float8e4m3fnuz, float8e5m2, float8e5m2fnuz, int4, and uint4 support - Transpose(21) - Missing float8e4m3fnuz, float8e5m2, float8e5m2fnuz, int4, and uint4 support - Unsqueeze(21) - Missing float8e4m3fnuz, float8e5m2, float8e5m2fnuz, int4, and uint4 support #### Unimplemented opset 21 features/ops - int4 and uint4 data type - QLinearMatMul(21) - GroupNormalization(21) - ai.onnx.ml.TreeEnsemble(5) ### 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. --> ### Disabled tests #### ORT Training orttraining/orttraining/test/python/orttraining_test_ort_apis_py_bindings.py - test_ort_custom_ops: Potential shape inference bug for custom ops #### Python quantization unit tests test/onnx/python/quantization (shape inference bug) - test_op_conv_transpose.py: test_quantize_conv_transpose_u8u8_fp16 - test_op_conv_transpose.py: test_quantize_conv_transpose_s8s8_fp16 - test_op_gemm.py: test_quantize_qop_gemm_s8s8 - test_op_gemm.py: test_quantize_qop_gemm_e4m3fn_same - test_op_gemm.py: test_quantize_qop_gemm_e4m3fn_p3 - test_op_matmul.py: test_quantize_matmul_u8u8_f16 - test_op_matmul.py: test_quantize_matmul_s8s8_f16 - test_op_matmul.py: test_quantize_matmul_s8s8_f16_entropy - test_op_matmul.py: test_quantize_matmul_s8s8_f16_percentile - test_op_matmul.py: test_quantize_matmul_s8s8_f16_distribution - test_op_relu.py: test_quantize_qop_relu_s8s8 #### ONNX tests - test_maxpool_2d_ceil_output_size_reduce_by_one: ONNX 1.16.0 fixed a maxpool output size bug and added this test. Enable this test when [ORT PR](https://github.com/microsoft/onnxruntime/pull/18377) is merged. Refer to original [ONNX PR](https://github.com/onnx/onnx/pull/5741). - test_ai_onnx_ml_tree_ensemble_set_membership_cpu: new unimplemented op ai.onnx.ml.TreeEnsemble - test_ai_onnx_ml_tree_ensemble_single_tree_cpu: same - test_ai_onnx_ml_tree_ensemble_set_membership_cuda: same - test_ai_onnx_ml_tree_ensemble_single_tree_cuda: same - test_cast_INT4_to_FLOAT_cpu: ORT Cast(21) impl doesn't support int4 yet - test_cast_INT4_to_INT8_cpu: same - test_cast_UINT4_to_FLOAT_cpu: same - test_cast_UINT4_to_UINT8_cpu: same - test_cast_INT4_to_FLOAT_cuda - test_cast_INT4_to_INT8_cuda - test_cast_UINT4_to_FLOAT_cuda - test_cast_UINT4_to_UINT8_cuda - test_constantofshape_float_ones_cuda: ConstantOfShape(21) not implemented for cuda - test_constantofshape_int_shape_zero_cuda: same - test_constantofshape_int_zeros_cuda: same - test_flatten_axis0_cuda: Flatten(21) not implemented for cuda - test_flatten_axis1_cuda: same - test_flatten_axis2_cuda: same - test_flatten_axis3_cuda: same - test_flatten_default_axis_cuda: same - test_flatten_negative_axis1_cuda: same - test_flatten_negative_axis2_cuda: same - test_flatten_negative_axis3_cuda: same - test_flatten_negative_axis4_cuda: same - test_qlinearmatmul_2D_int8_float16_cpu: QLinearMatMul(21) for onnx not implemented in ORT yet - test_qlinearmatmul_2D_int8_float32_cpu: same - test_qlinearmatmul_2D_uint8_float16_cpu: same - test_qlinearmatmul_2D_uint8_float32_cpu: same - test_qlinearmatmul_3D_int8_float16_cpu: same - test_qlinearmatmul_3D_int8_float32_cpu: same - test_qlinearmatmul_3D_uint8_float16_cpu: same - test_qlinearmatmul_3D_uint8_float32_cpu: same - test_qlinearmatmul_2D_int8_float16_cuda: same - test_qlinearmatmul_2D_int8_float32_cuda: same - test_qlinearmatmul_2D_uint8_float16_cuda: same - test_qlinearmatmul_2D_uint8_float32_cuda: same - test_qlinearmatmul_3D_int8_float16_cuda: same - test_qlinearmatmul_3D_int8_float32_cuda: same - test_qlinearmatmul_3D_uint8_float16_cuda: same - test_qlinearmatmul_3D_uint8_float32_cuda: same - test_size_cuda: Size(21) not implemented for cuda - test_size_example_cuda: same - test_dequantizelinear_blocked: Missing implementation for block dequant for DequantizeLinear(21) - test_quantizelinear_blocked_asymmetric: Missing implementation for block quant for QuantizeLinear(21) - test_quantizelinear_blocked_symmetric: Missing implementation for block quant for QuantizeLinear(21) --------- Signed-off-by: liqunfu <liqun.fu@microsoft.com> Signed-off-by: Ganesan Ramalingam <grama@microsoft.com> Co-authored-by: Ganesan Ramalingam <grama@microsoft.com> Co-authored-by: George Wu <jywu@microsoft.com> Co-authored-by: adrianlizarraga <adlizarraga@microsoft.com>
2024-04-12 16:46:49 +00:00
- Run `git grep -rn "onnx==1" .` to find other locations and update this document if necessary.
Add dev notes
2019-02-01 22:16:30 +00:00
Support per-test tolerances for ONNX tests (#11775) Prior to this every test shared the same tolerances. This meant that if an ONNX test failed due to a small but acceptable difference in output, the only alternative was to disable the test entirely. In op set 17, the DFT operator is being added. Without this change, the tests for that operator fail because the output is off by about 5e-5. It's better to keep test coverage for this new op rather than disable the test entirely. Also prior to this change, the global tolerances were not shared between C++, JavaScript, and Python tests. Now they are. Also fix various minor issues raised by linters. Unblocks https://github.com/microsoft/onnxruntime/issues/11640.
2022-06-14 22:12:23 +00:00
1. If there is any change to `cmake/external/onnx/onnx/*.in.proto`, you need to regenerate OnnxMl.cs.
[Building onnxruntime with Nuget](https://onnxruntime.ai/docs/build/inferencing.html#build-nuget-packages) will do
this.
Remove onnxruntime/core/protobuf (#8617) * remove onnxruntime/core/protobuf * Update How_To_Update_ONNX_Dev_Notes.md
2021-08-10 16:36:27 +00:00
Support per-test tolerances for ONNX tests (#11775) Prior to this every test shared the same tolerances. This meant that if an ONNX test failed due to a small but acceptable difference in output, the only alternative was to disable the test entirely. In op set 17, the DFT operator is being added. Without this change, the tests for that operator fail because the output is off by about 5e-5. It's better to keep test coverage for this new op rather than disable the test entirely. Also prior to this change, the global tolerances were not shared between C++, JavaScript, and Python tests. Now they are. Also fix various minor issues raised by linters. Unblocks https://github.com/microsoft/onnxruntime/issues/11640.
2022-06-14 22:12:23 +00:00
1. If you are updating ONNX from a released tag to a new commit, please ask Changming (@snnn) to deploy the new test
data along with other test models to our CI build machines. This is to ensure that our tests cover every ONNX opset.
Add dev notes
2019-02-01 22:16:30 +00:00
Update script to find optimizers that potentially need supported opset updates (#12330) * Update to handle multiline declarations for the kernels which are typical these days. * Update to new path for the cpu contrib_op kernel registrations. * Update tools/python/find_optimizer_opset_version_updates_required.py Co-authored-by: Justin Chu <justinchuby@users.noreply.github.com>
2022-08-03 21:37:27 +00:00
1. Send your PR, and **manually** queue a build for every packaging pipeline for your branch.
Add dev notes
2019-02-01 22:16:30 +00:00
Support per-test tolerances for ONNX tests (#11775) Prior to this every test shared the same tolerances. This meant that if an ONNX test failed due to a small but acceptable difference in output, the only alternative was to disable the test entirely. In op set 17, the DFT operator is being added. Without this change, the tests for that operator fail because the output is off by about 5e-5. It's better to keep test coverage for this new op rather than disable the test entirely. Also prior to this change, the global tolerances were not shared between C++, JavaScript, and Python tests. Now they are. Also fix various minor issues raised by linters. Unblocks https://github.com/microsoft/onnxruntime/issues/11640.
2022-06-14 22:12:23 +00:00
1. If there is a build failure in stage "Check out of dated documents" in WebAssembly CI pipeline, update ONNX Runtime
Web WebGL operator support document:
doc: add ort-web related instructions to update onnx doc (#8500) * doc: update instructions for ort web docs * revise readme
2021-08-06 22:09:11 +00:00
- Make sure Node.js is installed (see [Prerequisites](../js/README.md#Prerequisites) for instructions).
- Follow step 1 in [js/Build](../js/README.md#Build-2) to install dependencies).
- Follow instructions in [Generate document](../js/README.md#Generating-Document) to update document. Commit changes applied to file `docs/operators.md`.
Support per-test tolerances for ONNX tests (#11775) Prior to this every test shared the same tolerances. This meant that if an ONNX test failed due to a small but acceptable difference in output, the only alternative was to disable the test entirely. In op set 17, the DFT operator is being added. Without this change, the tests for that operator fail because the output is off by about 5e-5. It's better to keep test coverage for this new op rather than disable the test entirely. Also prior to this change, the global tolerances were not shared between C++, JavaScript, and Python tests. Now they are. Also fix various minor issues raised by linters. Unblocks https://github.com/microsoft/onnxruntime/issues/11640.
2022-06-14 22:12:23 +00:00
1. Usually some newly introduced tests will fail. Then you may need to update
Add dev notes
2019-02-01 22:16:30 +00:00
- [onnxruntime/test/onnx/main.cc](/onnxruntime/test/onnx/main.cc)
Remove onnxruntime/core/protobuf (#8617) * remove onnxruntime/core/protobuf * Update How_To_Update_ONNX_Dev_Notes.md
2021-08-10 16:36:27 +00:00
- [onnxruntime/test/providers/cpu/model_tests.cc](/onnxruntime/test/providers/cpu/model_tests.cc)
Remove exclusions for ONNX model tests that now pass. (#14337) ### Description <!-- Describe your changes. --> Remove exclusions for ONNX model tests that now pass due to kernels being implemented. Update ONNX update doc to point to correct location for tests. ### 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. --> Run as many tests as possible. Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
2023-01-23 22:04:27 +00:00
- [csharp/test/Microsoft.ML.OnnxRuntime.Tests.NetCoreApp/InferenceTest.netcore.cs](/csharp/test/Microsoft.ML.OnnxRuntime.Tests.NetCoreApp/InferenceTest.netcore.cs)
move backend test filters into data file (#3798) * move backend test filters into data file * update data * update data * update document * fix list for current_failing_tests_OPENVINO_CPU_FP32
2020-05-03 02:05:58 +00:00
- [onnxruntime/test/testdata/onnx_backend_test_series_filters.jsonc](/onnxruntime/test/testdata/onnx_backend_test_series_filters.jsonc)
Support per-test tolerances for ONNX tests (#11775) Prior to this every test shared the same tolerances. This meant that if an ONNX test failed due to a small but acceptable difference in output, the only alternative was to disable the test entirely. In op set 17, the DFT operator is being added. Without this change, the tests for that operator fail because the output is off by about 5e-5. It's better to keep test coverage for this new op rather than disable the test entirely. Also prior to this change, the global tolerances were not shared between C++, JavaScript, and Python tests. Now they are. Also fix various minor issues raised by linters. Unblocks https://github.com/microsoft/onnxruntime/issues/11640.
2022-06-14 22:12:23 +00:00
- [onnxruntime/test/testdata/onnx_backend_test_series_overrides.jsonc](/onnxruntime/test/testdata/onnx_backend_test_series_overrides.jsonc)
Update script to find optimizers that potentially need supported opset updates (#12330) * Update to handle multiline declarations for the kernels which are typical these days. * Update to new path for the cpu contrib_op kernel registrations. * Update tools/python/find_optimizer_opset_version_updates_required.py Co-authored-by: Justin Chu <justinchuby@users.noreply.github.com>
2022-08-03 21:37:27 +00:00
1. If an operator has changed we may need to update optimizers involving that operator.
- Run [find_optimizer_opset_version_updates_required.py](/tools/python/find_optimizer_opset_version_updates_required.py), compare with the output from the current main branch, and check for any new warnings.
- If there are new warnings contact the optimizer owner (which can usually be determined by looking at who edited the file most recently) or failing that ask the 'ONNX Runtime Shared Core' mailing list.
Reference in a new issue Copy permalink