Add new kernels #23220
Add new kernels #23220
Conversation
|
/azp run Big Models, Linux Android Emulator QNN CI Pipeline, Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline |
|
/azp run Linux OpenVINO CI Pipeline, Linux QNN CI Pipeline, MacOS CI Pipeline, ONNX Runtime Web CI Pipeline, Windows ARM64 QNN CI Pipeline, Windows CPU CI Pipeline, Windows GPU CUDA CI Pipeline |
|
/azp run Windows GPU DML CI Pipeline, Windows GPU Doc Gen CI Pipeline, Windows GPU TensorRT CI Pipeline, Windows x64 QNN CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline |
|
Azure Pipelines successfully started running 6 pipeline(s). |
|
Azure Pipelines successfully started running 5 pipeline(s). |
|
Azure Pipelines successfully started running 7 pipeline(s). |
| @@ -183,6 +183,22 @@ TEST(MathOpTest, DimWithZeroHandling) { | |||
| run(test5); | |||
| } | |||
|
|
|||
| TEST(MathOpTest, Add_int8) { | |||
There was a problem hiding this comment.
These tests are good. But, they are for C++ only. Would you please also add tests to ONNX so that a broader community will be benefited?
Like this:
https://github.com/onnx/onnx/blob/main/onnx/backend/test/case/node/mul.py#L35
Our pipelines run all ONNX node tests
|
You may need to disable the tests for TensorRT EP and DNNL EP. |
Description
This PR adds the kernels for
int8_t,int16_t, and unsigned int inputs forMul,Div,Add,Sub,Greater,Less,Equal,LessOrEqual, andGreaterOrEqual. The new kernels have been added for all versions of these operators that are supported by theONNXstandard.Motivation and Context
Similarly to #15358, this change eliminates the need for intermediate type casting for these data types.