Second round of cherry-pick

VERSION_NUMBER

@@ -1 +1 @@
-1.5.2
+1.6.0

docs/Versioning.md

@@ -26,11 +26,13 @@ For more details on ONNX Release versions, see [this page](https://github.com/on
 
 | ONNX Runtime release version | ONNX release version | ONNX opset version | ONNX ML opset version | Supported ONNX IR version | [Windows ML Availability](https://docs.microsoft.com/en-us/windows/ai/windows-ml/release-notes/)|
 |------------------------------|--------------------|--------------------|----------------------|------------------|------------------|
-| 1.5.2 | **1.7** down to 1.2 | 12 | 2 | 6 | Windows AI 1.5+ |
-| 1.5.1 | **1.7** down to 1.2 | 12 | 2 | 6 | Windows AI 1.5+ |
-| 1.4.0 | **1.7** down to 1.2 | 12 | 2 | 6 | Windows AI 1.4+ |
-| 1.3.1 | **1.7** down to 1.2 | 12 | 2 | 6 | Windows AI 1.4+ |
-| 1.3.0 | **1.7** down to 1.2 | 12 | 2 | 6 | Windows AI 1.3+ |
+| 1.6.0 | **1.8** down to 1.2 | 13 | 2 | 7 | Windows AI 1.6+ |
+| 1.5.3 | **1.7** down to 1.2 | 12 | 2 | 7 | Windows AI 1.5+ |
+| 1.5.2 | **1.7** down to 1.2 | 12 | 2 | 7 | Windows AI 1.5+ |
+| 1.5.1 | **1.7** down to 1.2 | 12 | 2 | 7 | Windows AI 1.5+ |
+| 1.4.0 | **1.7** down to 1.2 | 12 | 2 | 7 | Windows AI 1.4+ |
+| 1.3.1 | **1.7** down to 1.2 | 12 | 2 | 7 | Windows AI 1.4+ |
+| 1.3.0 | **1.7** down to 1.2 | 12 | 2 | 7 | Windows AI 1.3+ |
 | 1.2.0<br>1.1.2<br>1.1.1<br>1.1.0 | **1.6** down to 1.2 | 11 | 2 | 6 | Windows AI 1.3+ |
 | 1.0.0 | **1.6** down to 1.2 | 11 | 2 | 6 | Windows AI 1.3+ |
 | 0.5.0 | **1.5** down to 1.2 | 10 | 1 | 5 | Windows AI 1.3+ |

docs/python/README.rst

@@ -8,6 +8,16 @@ For more information on ONNX Runtime, please see `aka.ms/onnxruntime <https://ak
 Changes
 -------
 
+1.6.0
+^^^^^
+
+Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.6.0
+
+1.5.3
+^^^^^
+
+Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v1.5.3
+
 1.5.2
 ^^^^^
 

include/onnxruntime/core/session/onnxruntime_c_api.h

@@ -7,7 +7,7 @@
 #include <string.h>
 
 // This value is used in structures passed to ORT so that a newer version of ORT will still work with them
-#define ORT_API_VERSION 5
+#define ORT_API_VERSION 6
 
 #ifdef __cplusplus
 extern "C" {

nodejs/package.json

@@ -1,7 +1,7 @@
 {
   "name": "onnxruntime",
   "description": "Node.js binding of ONNXRuntime",
-  "version": "1.5.2",
+  "version": "1.6.0",
   "main": "./lib/index.js",
   "types": "./types/lib/index.d.ts",
   "scripts": {
@@ -69,4 +69,4 @@
   "dependencies": {
     "prebuild-install": "^5.3.5"
   }
-}
+}

onnxruntime/__init__.py

@@ -7,7 +7,7 @@
 For more information on ONNX Runtime, please see `aka.ms/onnxruntime <https://aka.ms/onnxruntime/>`_
 or the `Github project <https://github.com/microsoft/onnxruntime/>`_.
 """
-__version__ = "1.5.2"
+__version__ = "1.6.0"
 __author__ = "Microsoft"
 
 from onnxruntime.capi._pybind_state import get_all_providers, get_available_providers, get_device, set_seed, \

onnxruntime/core/optimizer/matmul_integer_to_float.cc

@@ -34,7 +34,7 @@ static bool CheckBiasShape(const TensorShapeProto* bias_shape) {
 /**
 MatMulIntegerToFloatFusion will fuse subgraph like below into MatMulIntegerToFloat:
 
- A   A_Zero B B_Zero  A_Scale) B_Scale  Bias (Const, Optional)
+ A   A_Zero B B_Zero  A_Scale  B_Scale  Bias (Const, Optional)
   \    |    |    /        \      /             |
    \   |    |   /          \    /              |
     \  |    |  /            \  /               |  
@@ -84,6 +84,13 @@ Status MatMulIntegerToFloatFusion::ApplyImpl(Graph& graph, bool& modified, int g
       continue;
     }
 
+    // A_Scale is scalar and B_Scale is scalar or 1D tensor
+    auto mul_node_input_defs = p_mul_node_right->InputDefs();
+    if (!optimizer_utils::IsScalar(*mul_node_input_defs[0]) ||
+        !optimizer_utils::IsScalar(*mul_node_input_defs[1])) {
+      continue;
+    }
+
     Node& cast_node = *graph.GetNode(p_cast_node->Index());
     Node& matmulinteger_node = *graph.GetNode(p_matmulinteger_node->Index());
     Node& mul_node_right = *graph.GetNode(p_mul_node_right->Index());

onnxruntime/core/optimizer/utils.cc

@@ -24,7 +24,7 @@ bool IsFloatingPointDataType(const ONNX_NAMESPACE::TensorProto& tensor_proto) {
   return tensor_proto.data_type() == ONNX_NAMESPACE::TensorProto_DataType_FLOAT || tensor_proto.data_type() == ONNX_NAMESPACE::TensorProto_DataType_FLOAT16 || tensor_proto.data_type() == ONNX_NAMESPACE::TensorProto_DataType_DOUBLE;
 }
 
-inline bool IsScalar(const NodeArg& input_arg) {
+bool IsScalar(const NodeArg& input_arg) {
   auto shape = input_arg.Shape();
   if (shape == nullptr) {
     // shape inferencing wasn't able to populate shape information for this NodeArg

onnxruntime/core/optimizer/utils.h

@@ -15,6 +15,9 @@ namespace optimizer_utils {
 // Check if TensorProto contains a floating point type.
 bool IsFloatingPointDataType(const ONNX_NAMESPACE::TensorProto& tensor_proto);
 
+// Check if input is a scalar
+bool IsScalar(const NodeArg& input_arg);
+
 /** Check whether a input is initializer with specified float value.
 @param expected_value is the expected value of the initializer.
 @param is_constant means whether the initializer is required to be constant.
@@ -60,7 +63,7 @@ bool ValidateShape(const NodeArg& node_arg, const std::initializer_list<int64_t>
 */
 bool CompareShape(const ONNX_NAMESPACE::TensorShapeProto& node_arg_shape, const ONNX_NAMESPACE::TensorShapeProto& node_arg_other_shape);
 
-/** Check check whether each dimension is known for shape of node_arg
+/** Check whether each dimension is known for shape of node_arg
 @returns false when shape is nullptr, or total dimension is not same as expected_dim_size length,
          or any dim is unknown (without dim value).
 */

onnxruntime/core/providers/cpu/ml/tree_ensemble_classifier.cc

@@ -139,7 +139,7 @@ template <typename T>
 TreeEnsembleClassifier<T>::TreeEnsembleClassifier(const OpKernelInfo& info)
     : OpKernel(info),
       tree_ensemble_(
-          100,
+          80,
           50,
           info.GetAttrOrDefault<std::string>("aggregate_function", "SUM"),
           info.GetAttrsOrDefault<float>("base_values"),