Update operator kernel table to include DML operators (#12887)

* Fix bug in pybind get_all_operator_schema due to premature reference dropping
* Add updated operator kernels markdown table
* Update build.py to include documentation generation for DML operators too
* Update GPU pipeline to include DML in the build to so operators can be generated.
* Use a separate pipeline stage, feedback from Changming and Scott
* Appease annoying Python linter
* Add onnxruntime_BUILD_UNIT_TESTS=OFF and remove stale --use_dml in cuda stage

docs/OperatorKernels.md

@@ -6,6 +6,7 @@ Do not modify directly.*
 
 - [CPUExecutionProvider](#cpuexecutionprovider)
 - [CUDAExecutionProvider](#cudaexecutionprovider)
+- [DmlExecutionProvider](#dmlexecutionprovider)
 
 ---------------
 
@@ -755,6 +756,311 @@ Do not modify directly.*
 |Xor|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T1**|7+|**T** = tensor(bool)<br/> **T1** = tensor(bool)|
 | |
 | |
+<a name="dmlexecutionprovider"/>
+
+## Operators implemented by DmlExecutionProvider
+
+| Op Name | Parameters | OpSet Version | Types Supported |
+|---------|------------|---------------|-----------------|
+|**Operator Domain:** *ai.onnx*||||
+|Abs|*in* X:**T**<br> *out* Y:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|||6+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|Acos|*in* input:**T**<br> *out* output:**T**|7+|**T** = tensor(float), tensor(float16)|
+|Acosh|*in* input:**T**<br> *out* output:**T**|9+|**T** = tensor(float), tensor(float16)|
+|Add|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T**|14+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||7+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Affine|*in* X:**T**<br> *out* Y:**T**|1+|**T** = tensor(float), tensor(float16)|
+|And|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T1**|7+|**T** = tensor(bool)|
+|ArgMax|*in* data:**T**<br> *out* reduced:**tensor(int64)**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||12+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||1+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|ArgMin|*in* data:**T**<br> *out* reduced:**tensor(int64)**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||12+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||1+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Asin|*in* input:**T**<br> *out* output:**T**|7+|**T** = tensor(float), tensor(float16)|
+|Asinh|*in* input:**T**<br> *out* output:**T**|9+|**T** = tensor(float), tensor(float16)|
+|Atan|*in* input:**T**<br> *out* output:**T**|7+|**T** = tensor(float), tensor(float16)|
+|Atanh|*in* input:**T**<br> *out* output:**T**|9+|**T** = tensor(float), tensor(float16)|
+|AveragePool|*in* X:**T**<br> *out* Y:**T**|11+|**T** = tensor(float), tensor(float16)|
+|||10+|**T** = tensor(float), tensor(float16)|
+|||7+|**T** = tensor(float), tensor(float16)|
+|BatchNormalization|*in* X:**T**<br> *in* scale:**T**<br> *in* B:**T**<br> *in* input_mean:**U**<br> *in* input_var:**U**<br> *out* Y:**T**<br> *out* running_mean:**U**<br> *out* running_var:**U**<br><br>or<br><br>*in* X:**T**<br> *in* scale:**T**<br> *in* B:**T**<br> *in* mean:**T**<br> *in* var:**T**<br> *out* Y:**T**<br> *out* mean:**T**<br> *out* var:**T**<br> *out* saved_mean:**T**<br> *out* saved_var:**T**<br><br>or<br><br>*in* X:**T**<br> *in* scale:**T1**<br> *in* B:**T1**<br> *in* input_mean:**T2**<br> *in* input_var:**T2**<br> *out* Y:**T**<br> *out* running_mean:**T2**<br> *out* running_var:**T2**|15+|**T** = tensor(float), tensor(float16)|
+|||14+|**T** = tensor(float), tensor(float16)|
+|||9+|**T** = tensor(float), tensor(float16)|
+|||7+|**T** = tensor(float), tensor(float16)|
+|BitShift|*in* X:**T**<br> *in* Y:**T**<br> *out* Z:**T**|11+|**T** = tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Cast|*in* input:**T1**<br> *out* output:**T2**|13+|**T1** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T2** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||9+|**T1** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T2** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||6+|**T1** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T2** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|CastLike|*in* input:**T1**<br> *in* target_type:**T2**<br> *out* output:**T2**|15+|**T1** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T2** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Ceil|*in* X:**T**<br> *out* Y:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|Celu|*in* X:**T**<br> *out* Y:**T**|12+|**T** = tensor(float), tensor(float16)|
+|Clip|*in* input:**T**<br> *in* min:**T**<br> *in* max:**T**<br> *out* output:**T**<br><br>or<br><br>*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||12+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|Concat|*in* inputs:**T**<br> *out* concat_result:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||4+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|ConstantOfShape|*in* input:**T1**<br> *out* output:**T2**|9+|**T1** = tensor(int64)<br/> **T2** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Conv|*in* X:**T**<br> *in* W:**T**<br> *in* B:**T**<br> *out* Y:**T**|11+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|ConvInteger|*in* x:**T1**<br> *in* w:**T2**<br> *in* x_zero_point:**T1**<br> *in* w_zero_point:**T2**<br> *out* y:**T3**|10+|**T1** = tensor(int8), tensor(uint8)<br/> **T2** = tensor(int8), tensor(uint8)<br/> **T3** = tensor(int32)|
+|ConvTranspose|*in* X:**T**<br> *in* W:**T**<br> *in* B:**T**<br> *out* Y:**T**|11+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|Cos|*in* input:**T**<br> *out* output:**T**|7+|**T** = tensor(float), tensor(float16)|
+|Cosh|*in* input:**T**<br> *out* output:**T**|9+|**T** = tensor(float), tensor(float16)|
+|Crop|*in* input:**T**<br> *out* output:**T**|1+|**T** = tensor(float), tensor(float16)|
+|CumSum|*in* x:**T**<br> *in* axis:**T2**<br> *out* y:**T**|14+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|||11+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|DepthToSpace|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||1+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|DequantizeLinear|*in* x:**T**<br> *in* x_scale:**tensor(float)**<br> *in* x_zero_point:**T**<br> *out* y:**tensor(float)**|13+|**T** = tensor(int32), tensor(int8), tensor(uint8)|
+|||10+|**T** = tensor(int32), tensor(int8), tensor(uint8)|
+|Div|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T**|14+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|||13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|||7+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|Dropout|*in* data:**T**<br> *in* ratio:**T1**<br> *in* training_mode:**T2**<br> *out* output:**T**<br> *out* mask:**T2**<br><br>or<br><br>*in* data:**T**<br> *out* output:**T**<br> *out* mask:**T**<br><br>or<br><br>*in* data:**T**<br> *out* output:**T**<br> *out* mask:**T1**|7+|**T** = tensor(float), tensor(float16)|
+|DynamicQuantizeLinear|*in* x:**T1**<br> *out* y:**T2**<br> *out* y_scale:**tensor(float)**<br> *out* y_zero_point:**T2**|11+|**T1** = tensor(float)<br/> **T2** = tensor(uint8)|
+|Einsum|*in* Inputs:**T**<br> *out* Output:**T**|12+|**T** = tensor(float), tensor(float16)|
+|Elu|*in* X:**T**<br> *out* Y:**T**|6+|**T** = tensor(float), tensor(float16)|
+|Equal|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T1**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(bool)|
+|||11+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(bool)|
+|||7+|**T** = tensor(float), tensor(float16)<br/> **T1** = tensor(bool)|
+|Erf|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||9+|**T** = tensor(float), tensor(float16)|
+|Exp|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|Expand|*in* input:**T**<br> *in* shape:**tensor(int64)**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||8+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|EyeLike|*in* input:**T1**<br> *out* output:**T2**|9+|**T1** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T2** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Flatten|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||9+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||1+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Floor|*in* X:**T**<br> *out* Y:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|GRU|*in* X:**T**<br> *in* W:**T**<br> *in* R:**T**<br> *in* B:**T**<br> *in* sequence_lens:**T1**<br> *in* initial_h:**T**<br> *out* Y:**T**<br> *out* Y_h:**T**|14+|**T** = tensor(float), tensor(float16)|
+|||7+|**T** = tensor(float), tensor(float16)|
+|Gather|*in* data:**T**<br> *in* indices:**Tind**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|||1+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|GatherElements|*in* data:**T**<br> *in* indices:**Tind**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|GatherND|*in* data:**T**<br> *in* indices:**tensor(int64)**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||12+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Gemm|*in* A:**T**<br> *in* B:**T**<br> *in* C:**T**<br> *out* Y:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||11+|**T** = tensor(float), tensor(float16)|
+|||9+|**T** = tensor(float), tensor(float16)|
+|||7+|**T** = tensor(float), tensor(float16)|
+|GlobalAveragePool|*in* X:**T**<br> *out* Y:**T**|1+|**T** = tensor(float), tensor(float16)|
+|GlobalLpPool|*in* X:**T**<br> *out* Y:**T**|2+|**T** = tensor(float), tensor(float16)|
+|GlobalMaxPool|*in* X:**T**<br> *out* Y:**T**|1+|**T** = tensor(float), tensor(float16)|
+|Greater|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T1**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(bool)|
+|||9+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(bool)|
+|||7+|**T** = tensor(float), tensor(float16)<br/> **T1** = tensor(bool)|
+|GreaterOrEqual|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T1**|12+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(bool)|
+|HardSigmoid|*in* X:**T**<br> *out* Y:**T**|6+|**T** = tensor(float), tensor(float16)|
+|Hardmax|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||11+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|Identity|*in* input:**T**<br> *out* output:**T**<br><br>or<br><br>*in* input:**V**<br> *out* output:**V**|14+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||1+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|ImageScaler|*in* input:**T**<br> *out* output:**T**|1+|**T** = tensor(float), tensor(float16)|
+|InstanceNormalization|*in* input:**T**<br> *in* scale:**T**<br> *in* B:**T**<br> *out* output:**T**|6+|**T** = tensor(float), tensor(float16)|
+|IsInf|*in* X:**T1**<br> *out* Y:**T2**|10+|**T1** = tensor(float)<br/> **T2** = tensor(bool)|
+|IsNaN|*in* X:**T1**<br> *out* Y:**T2**|13+|**T1** = tensor(float), tensor(float16)<br/> **T2** = tensor(bool)|
+|||9+|**T1** = tensor(float), tensor(float16)<br/> **T2** = tensor(bool)|
+|LRN|*in* X:**T**<br> *out* Y:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|LSTM|*in* X:**T**<br> *in* W:**T**<br> *in* R:**T**<br> *in* B:**T**<br> *in* sequence_lens:**T1**<br> *in* initial_h:**T**<br> *in* initial_c:**T**<br> *in* P:**T**<br> *out* Y:**T**<br> *out* Y_h:**T**<br> *out* Y_c:**T**|14+|**T** = tensor(float), tensor(float16)|
+|||7+|**T** = tensor(float), tensor(float16)|
+|LeakyRelu|*in* X:**T**<br> *out* Y:**T**|6+|**T** = tensor(float), tensor(float16)|
+|Less|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T1**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(bool)|
+|||9+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(bool)|
+|||7+|**T** = tensor(float), tensor(float16)<br/> **T1** = tensor(bool)|
+|LessOrEqual|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T1**|12+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T1** = tensor(bool)|
+|Log|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|LogSoftmax|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||11+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|LpNormalization|*in* input:**T**<br> *out* output:**T**|1+|**T** = tensor(float), tensor(float16)|
+|LpPool|*in* X:**T**<br> *out* Y:**T**|11+|**T** = tensor(float), tensor(float16)|
+|||2+|**T** = tensor(float), tensor(float16)|
+|MatMul|*in* A:**T**<br> *in* B:**T**<br> *out* Y:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||9+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|MatMulInteger|*in* A:**T1**<br> *in* B:**T2**<br> *in* a_zero_point:**T1**<br> *in* b_zero_point:**T2**<br> *out* Y:**T3**|10+|**T1** = tensor(int8), tensor(uint8)<br/> **T2** = tensor(int8), tensor(uint8)<br/> **T3** = tensor(int32)|
+|Max|*in* data_0:**T**<br> *out* max:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||12+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||8+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|MaxPool|*in* X:**T**<br> *out* Y:**T**<br><br>or<br><br>*in* X:**T**<br> *out* Y:**T**<br> *out* Indices:**I**|12+|**I** = tensor(int64)<br/> **T** = tensor(float), tensor(float16), tensor(int8), tensor(uint8)|
+|||11+|**I** = tensor(int64)<br/> **T** = tensor(float), tensor(float16), tensor(int8), tensor(uint8)|
+|||10+|**I** = tensor(int64)<br/> **T** = tensor(float), tensor(float16), tensor(int8), tensor(uint8)|
+|||8+|**I** = tensor(int64)<br/> **T** = tensor(float), tensor(float16), tensor(int8), tensor(uint8)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|MaxRoiPool|*in* X:**T**<br> *in* rois:**T**<br> *out* Y:**T**|1+|**T** = tensor(float), tensor(float16)|
+|MaxUnpool|*in* X:**T1**<br> *in* I:**T2**<br> *in* output_shape:**T2**<br> *out* output:**T1**|11+|**T1** = tensor(float), tensor(float16)<br/> **T2** = tensor(int64)|
+|||9+|**T1** = tensor(float), tensor(float16)<br/> **T2** = tensor(int64)|
+|Mean|*in* data_0:**T**<br> *out* mean:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||8+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|MeanVarianceNormalization|*in* X:**T**<br> *out* Y:**T**<br><br>or<br><br>*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||9+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|MemcpyFromHost|*in* X:**T**<br> *out* Y:**T**|1+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|MemcpyToHost|*in* X:**T**<br> *out* Y:**T**|1+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Min|*in* data_0:**T**<br> *out* min:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||12+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||8+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|Mod|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|||10+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|Mul|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T**|14+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||7+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Neg|*in* X:**T**<br> *out* Y:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8)|
+|||6+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8)|
+|Not|*in* X:**T**<br> *out* Y:**T**|1+|**T** = tensor(bool)|
+|OneHot|*in* indices:**T1**<br> *in* depth:**T2**<br> *in* values:**T3**<br> *out* output:**T3**|11+|**T1** = tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)<br/> **T2** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T3** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||9+|**T1** = tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)<br/> **T2** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T3** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Or|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T1**|7+|**T** = tensor(bool)|
+|PRelu|*in* X:**T**<br> *in* slope:**T**<br> *out* Y:**T**|9+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8)|
+|||7+|**T** = tensor(float), tensor(float16)|
+|Pad|*in* data:**T**<br> *in* pads:**tensor(int64)**<br> *in* constant_value:**T**<br> *out* output:**T**<br><br>or<br><br>*in* data:**T**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||2+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|ParametricSoftplus|*in* X:**T**<br> *out* Y:**T**|1+|**T** = tensor(float), tensor(float16)|
+|Pow|*in* X:**T**<br> *in* Y:**T**<br> *out* Z:**T**<br><br>or<br><br>*in* X:**T**<br> *in* Y:**T1**<br> *out* Z:**T**|15+|**T** = tensor(float), tensor(float16), tensor(int32)<br/> **T1** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|||13+|**T** = tensor(float), tensor(float16), tensor(int32)<br/> **T1** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|||12+|**T** = tensor(float), tensor(float16), tensor(int32)<br/> **T1** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|||7+|**T** = tensor(float), tensor(float16)|
+|QLinearConv|*in* x:**T1**<br> *in* x_scale:**tensor(float)**<br> *in* x_zero_point:**T1**<br> *in* w:**T2**<br> *in* w_scale:**tensor(float)**<br> *in* w_zero_point:**T2**<br> *in* y_scale:**tensor(float)**<br> *in* y_zero_point:**T3**<br> *in* B:**T4**<br> *out* y:**T3**|10+|**T1** = tensor(int8), tensor(uint8)<br/> **T2** = tensor(int8), tensor(uint8)<br/> **T3** = tensor(int8), tensor(uint8)<br/> **T4** = tensor(int32)|
+|QLinearMatMul|*in* a:**T1**<br> *in* a_scale:**tensor(float)**<br> *in* a_zero_point:**T1**<br> *in* b:**T2**<br> *in* b_scale:**tensor(float)**<br> *in* b_zero_point:**T2**<br> *in* y_scale:**tensor(float)**<br> *in* y_zero_point:**T3**<br> *out* y:**T3**|10+|**T1** = tensor(int8), tensor(uint8)<br/> **T2** = tensor(int8), tensor(uint8)<br/> **T3** = tensor(int8), tensor(uint8)|
+|QuantizeLinear|*in* x:**T1**<br> *in* y_scale:**tensor(float)**<br> *in* y_zero_point:**T2**<br> *out* y:**T2**|13+|**T1** = tensor(float), tensor(int32)<br/> **T2** = tensor(int8), tensor(uint8)|
+|||10+|**T1** = tensor(float), tensor(int32)<br/> **T2** = tensor(int8), tensor(uint8)|
+|RNN|*in* X:**T**<br> *in* W:**T**<br> *in* R:**T**<br> *in* B:**T**<br> *in* sequence_lens:**T1**<br> *in* initial_h:**T**<br> *out* Y:**T**<br> *out* Y_h:**T**|14+|**T** = tensor(float), tensor(float16)|
+|||7+|**T** = tensor(float), tensor(float16)|
+|Range|*in* start:**T**<br> *in* limit:**T**<br> *in* delta:**T**<br> *out* output:**T**|11+|**T** = tensor(float), tensor(int16), tensor(int32), tensor(int64)|
+|Reciprocal|*in* X:**T**<br> *out* Y:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|ReduceL1|*in* data:**T**<br> *out* reduced:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|||11+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|||1+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|ReduceL2|*in* data:**T**<br> *out* reduced:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||11+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|ReduceLogSum|*in* data:**T**<br> *out* reduced:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||11+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|ReduceLogSumExp|*in* data:**T**<br> *out* reduced:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||11+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|ReduceMax|*in* data:**T**<br> *out* reduced:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||12+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|ReduceMean|*in* data:**T**<br> *out* reduced:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||11+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|ReduceMin|*in* data:**T**<br> *out* reduced:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||12+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|ReduceProd|*in* data:**T**<br> *out* reduced:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|||11+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|||1+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|ReduceSum|*in* data:**T**<br> *in* axes:**tensor(int64)**<br> *out* reduced:**T**<br><br>or<br><br>*in* data:**T**<br> *out* reduced:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|||11+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|||1+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|ReduceSumSquare|*in* data:**T**<br> *out* reduced:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|||11+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|||1+|**T** = tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
+|Relu|*in* X:**T**<br> *out* Y:**T**|14+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8)|
+|||13+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|Reshape|*in* data:**T**<br> *in* shape:**tensor(int64)**<br> *out* reshaped:**T**<br><br>or<br><br>*in* data:**T**<br> *out* reshaped:**T**|14+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||5+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Resize|*in* X:**T**<br> *in* scales:**tensor(float)**<br> *out* Y:**T**<br><br>or<br><br>*in* X:**T1**<br> *in* roi:**T2**<br> *in* scales:**tensor(float)**<br> *in* sizes:**tensor(int64)**<br> *out* Y:**T1**|13+|**T1** = tensor(float), tensor(float16)<br/> **T2** = tensor(float), tensor(float16)|
+|||11+|**T1** = tensor(float), tensor(float16)<br/> **T2** = tensor(float), tensor(float16)|
+|||10+|**T** = tensor(float), tensor(float16)|
+|ReverseSequence|*in* input:**T**<br> *in* sequence_lens:**tensor(int64)**<br> *out* Y:**T**|10+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|RoiAlign|*in* X:**T1**<br> *in* rois:**T1**<br> *in* batch_indices:**T2**<br> *out* Y:**T1**|10+|**T1** = tensor(float), tensor(float16)<br/> **T2** = tensor(int32), tensor(int64)|
+|Round|*in* X:**T**<br> *out* Y:**T**|11+|**T** = tensor(float), tensor(float16)|
+|ScaledTanh|*in* input:**T**<br> *out* output:**T**|1+|**T** = tensor(float), tensor(float16)|
+|Scatter|*in* data:**T**<br> *in* indices:**Tind**<br> *in* updates:**T**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|||9+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|ScatterElements|*in* data:**T**<br> *in* indices:**Tind**<br> *in* updates:**T**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|ScatterND|*in* data:**T**<br> *in* indices:**tensor(int64)**<br> *in* updates:**T**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Selu|*in* X:**T**<br> *out* Y:**T**|6+|**T** = tensor(float), tensor(float16)|
+|Shrink|*in* input:**T**<br> *out* output:**T**|9+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|Sigmoid|*in* X:**T**<br> *out* Y:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|Sign|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|||9+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|Sin|*in* input:**T**<br> *out* output:**T**|7+|**T** = tensor(float), tensor(float16)|
+|Sinh|*in* input:**T**<br> *out* output:**T**|9+|**T** = tensor(float), tensor(float16)|
+|Slice|*in* data:**T**<br> *in* starts:**Tind**<br> *in* ends:**Tind**<br> *in* axes:**Tind**<br> *in* steps:**Tind**<br> *out* output:**T**<br><br>or<br><br>*in* data:**T**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|||10+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **Tind** = tensor(int32), tensor(int64)|
+|||1+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Softmax|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||11+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|Softplus|*in* X:**T**<br> *out* Y:**T**|1+|**T** = tensor(float), tensor(float16)|
+|Softsign|*in* input:**T**<br> *out* output:**T**|1+|**T** = tensor(float), tensor(float16)|
+|SpaceToDepth|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||1+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Split|*in* input:**T**<br> *in* split:**T**<br> *out* outputs...:**T**<br><br>or<br><br>*in* input:**T**<br> *in* split:**tensor(int64)**<br> *out* outputs:**T**<br><br>or<br><br>*in* input:**T**<br> *out* outputs:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||2+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Sqrt|*in* X:**T**<br> *out* Y:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|Squeeze|*in* data:**T**<br> *in* axes:**tensor(int64)**<br> *out* squeezed:**T**<br><br>or<br><br>*in* data:**T**<br> *out* squeezed:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||1+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Sub|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T**|14+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||13+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||7+|**T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Sum|*in* data_0:**T**<br> *out* sum:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||8+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|Tan|*in* input:**T**<br> *out* output:**T**|7+|**T** = tensor(float), tensor(float16)|
+|Tanh|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float), tensor(float16)|
+|||6+|**T** = tensor(float), tensor(float16)|
+|ThresholdedRelu|*in* X:**T**<br> *out* Y:**T**|10+|**T** = tensor(float), tensor(float16)|
+|||1+|**T** = tensor(float), tensor(float16)|
+|Tile|*in* input:**T**<br> *in* repeats:**T1**<br> *out* output:**T**<br><br>or<br><br>*in* input:**T**<br> *in* tiles:**T**<br> *in* axis:**T**<br> *out* output:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||6+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|TopK|*in* X:**T**<br> *in* K:**tensor(int64)**<br> *out* Values:**T**<br> *out* Indices:**I**<br><br>or<br><br>*in* X:**T**<br> *out* Values:**T**<br> *out* Indices:**I**|11+|**I** = tensor(int64)<br/> **T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||10+|**I** = tensor(int64)<br/> **T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||1+|**I** = tensor(int64)<br/> **T** = tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Transpose|*in* data:**T**<br> *out* transposed:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||1+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Trilu|*in* input:**T**<br> *in* k:**tensor(int64)**<br> *out* output:**T**|14+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Unsqueeze|*in* data:**T**<br> *in* axes:**tensor(int64)**<br> *out* expanded:**T**<br><br>or<br><br>*in* data:**T**<br> *out* expanded:**T**|13+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||11+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|||1+|**T** = tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
+|Upsample|*in* X:**T**<br> *in* scales:**tensor(float)**<br> *out* Y:**T**<br><br>or<br><br>*in* X:**T**<br> *out* Y:**T**|10+|**T** = tensor(float), tensor(float16)|
+|||9+|**T** = tensor(float), tensor(float16)|
+|||7+|**T** = tensor(float), tensor(float16)|
+|Where|*in* condition:**B**<br> *in* X:**T**<br> *in* Y:**T**<br> *out* output:**T**|9+|**B** = tensor(bool)<br/> **T** = tensor(bool), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint8)|
+|Xor|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T1**|7+|**T** = tensor(bool)|
+| |
+| |
 |**Operator Domain:** *com.microsoft*||||
 |Attention|*in* input:**T**<br> *in* weight:**T**<br> *in* bias:**T**<br> *in* mask_index:**M**<br> *in* past:**T**<br> *in* extra_add:**T**<br> *out* output:**T**<br> *out* present:**T**|1+|**T** = tensor(float), tensor(float16)|
 |BeamSearch|*in* input_ids:**I**<br> *in* max_length:**I**<br> *in* min_length:**I**<br> *in* num_beams:**I**<br> *in* num_return_sequences:**I**<br> *in* length_penalty:**T**<br> *in* repetition_penalty:**T**<br> *in* vocab_mask:**M**<br> *in* prefix_vocab_mask:**M**<br> *in* attention_mask:**I**<br> *out* sequences:**I**<br> *out* sequences_scores:**T**<br> *out* scores:**T**|1+|**T** = tensor(float), tensor(float16)|

onnxruntime/python/onnxruntime_pybind_schema.cc

@@ -79,9 +79,8 @@ void addGlobalSchemaFunctions(pybind11::module& m) {
         };
 
       for (const auto& f : factories) {
-          for (const auto& m : f->CreateProvider()
-                                   ->GetKernelRegistry()
-                                   ->GetKernelCreateMap()) {
+          auto kernel_registry = f->CreateProvider()->GetKernelRegistry();
+          for (const auto& m : kernel_registry->GetKernelCreateMap()) {
             result.emplace_back(*(m.second.kernel_def));
           }
         }

tools/ci_build/build.py

@@ -2307,10 +2307,19 @@ def generate_documentation(source_dir, build_dir, configs, validate):
         [sys.executable, "gen_contrib_doc.py", "--output_path", contrib_op_doc_path, "--domains", "com.microsoft"],
         cwd=cwd,
     )
-    # we currently limit the documentation created by a build to the CPU and CUDA EPs.
+    # we currently limit the documentation created by a build to a subset of EP's.
     # Run get_opkernel_doc.py directly if you need/want documentation from other EPs that are enabled in the build.
     run_subprocess(
-        [sys.executable, "gen_opkernel_doc.py", "--output_path", opkernel_doc_path, "--providers", "CPU", "CUDA"],
+        [
+            sys.executable,
+            "gen_opkernel_doc.py",
+            "--output_path",
+            opkernel_doc_path,
+            "--providers",
+            "CPU",
+            "CUDA",
+            "DML",
+        ],
         cwd=cwd,
     )
 

tools/ci_build/github/azure-pipelines/win-gpu-ci-pipeline.yml

@@ -13,7 +13,7 @@ stages:
         BuildConfig: 'RelWithDebInfo'
         EnvSetupScript: setup_env_cuda_11.bat
         buildArch: x64
-        additionalBuildFlags: --enable_pybind --build_java --build_nodejs --use_cuda --cuda_version=11.4 --cuda_home="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.4"  --gen_doc validate --enable_cuda_profiling --cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=52
+        additionalBuildFlags: --enable_pybind --build_java --build_nodejs --use_cuda --cuda_version=11.4 --cuda_home="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.4" --enable_cuda_profiling --cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=52
         msbuildPlatform: x64
         isX86: false
         job_name_suffix: x64_RelWithDebInfo
@@ -21,8 +21,6 @@ stages:
         RunStaticCodeAnalysis: false
         ORT_EP_NAME: CUDA
         MachinePool: onnxruntime-Win2019-GPU
-        DocUpdateNeeded: true
-
 
 - stage: training
   dependsOn: []
@@ -41,7 +39,7 @@ stages:
         ORT_EP_NAME: CUDA
         MachinePool: onnxruntime-Win2019-GPU-training
         isTraining: true
-     
+
 - stage: dml
   dependsOn: []
   jobs:
@@ -59,3 +57,20 @@ stages:
         ORT_EP_NAME: DML
         MachinePool: onnxruntime-Win2019-GPU-dml
 
+- stage: kernelDocumentation
+  dependsOn: []
+  jobs:
+    - template: templates/win-gpu-ci.yml
+      parameters:
+        BuildConfig: 'RelWithDebInfo'
+        EnvSetupScript: setup_env_cuda_11.bat
+        buildArch: x64
+        additionalBuildFlags: --gen_doc validate --skip_tests --enable_pybind --use_dml --use_cuda --cuda_version=11.4 --cuda_home="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.4" --enable_cuda_profiling --cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=52 --cmake_extra_defines onnxruntime_BUILD_UNIT_TESTS=OFF
+        msbuildPlatform: x64
+        isX86: false
+        job_name_suffix: x64_RelWithDebInfo
+        RunOnnxRuntimeTests: false
+        RunStaticCodeAnalysis: false
+        ORT_EP_NAME: CUDA # It doesn't really matter which EP is selected here since this stage is for documentation.
+        MachinePool: onnxruntime-Win2019-GPU
+        DocUpdateNeeded: true