[ONNX] [apache#8838] QLinearLeakyRelu contrib op (apache#9063)

* [ONNX] QLinearLeakyRelu contrib op

* Add comment

* jostle ci

* jostle ci

python/tvm/relay/frontend/onnx.py

@@ -3531,6 +3531,28 @@ def _impl_v10(cls, inputs, attr, params):
         return _qnn.op.quantize(out, y_scale, y_zero_point, out_dtype=dtype)
 
 
+class QLinearLeakyRelu(OnnxOpConverter):
+    """Operator converter for QLinearLeakyRelu from Microsoft onnxruntime contrib opset."""
+
+    @classmethod
+    def _impl_v10(cls, inputs, attr, params):
+
+        a_scale = get_scalar(inputs[1], params)
+        a_zero_point = get_scalar(inputs[2], params, "int32")
+        y_scale = fold_constant(get_scalar(inputs[3], params))
+        y_zero_point = get_scalar(inputs[4], params, "int32")
+        alpha = float(attr.get("alpha", 1.0))
+
+        dtype = infer_type(inputs[0]).checked_type.dtype
+
+        # Onnxruntime doesn't actually do this op in integer, they dequantize to fp32
+        # and then requantize afer (according to documentation below)
+        # https://github.com/microsoft/onnxruntime/blob/master/docs/ContribOperators.md#com.microsoft.QLinearLeakyRelu
+        a = _qnn.op.dequantize(inputs[0], a_scale, a_zero_point)
+        out = _op.nn.leaky_relu(a, alpha)
+        return _qnn.op.quantize(out, y_scale, y_zero_point, out_dtype=dtype)
+
+
 class QLinearSigmoid(OnnxOpConverter):
     """Operator converter for QLinearSigmoid from Microsoft onnxruntime contrib opset."""
 
@@ -4217,6 +4239,7 @@ def _get_convert_map(opset):
         "ConvInteger": ConvInteger.get_converter(opset),
         "QLinearAveragePool": QLinearAveragePool.get_converter(opset),
         "QLinearGlobalAveragePool": QLinearGlobalAveragePool.get_converter(opset),
+        "QLinearLeakyRelu": QLinearLeakyRelu.get_converter(opset),
         # Random number generation.
         "RandomUniform": RandomUniform.get_converter(opset),
         # Loss functions / training

tests/python/frontend/onnx/test_forward.py

@@ -5525,6 +5525,27 @@ def verify_qlinearmul(a_shape, b_shape, c_shape):
     verify_qlinearmul([5, 1, 7], [2, 7], [5, 2, 7])
 
 
+@tvm.testing.parametrize_targets
+def test_qlinearleakyrelu(target, dev):
+    def verify_qlinearleakyrelu(inshape, kwargs):
+
+        in_array = np.random.random(inshape).astype("float32")
+        node = helper.make_node("LeakyRelu", ["X"], ["Y"], **kwargs)
+
+        graph = helper.make_graph(
+            [node],
+            "qlinearRelu_test",
+            inputs=[helper.make_tensor_value_info("X", TensorProto.FLOAT, list(in_array.shape))],
+            outputs=[helper.make_tensor_value_info("Y", TensorProto.FLOAT, list(in_array.shape))],
+        )
+        model = helper.make_model(graph, producer_name="qlinearRelu_test")
+        quantize_and_verify_with_ort(model, ["X"], [in_array.shape], target, dev)
+
+    verify_qlinearleakyrelu([2, 4, 5, 6], {"alpha": 0.25})
+    verify_qlinearleakyrelu([6, 5, 6, 7], {"alpha": 0.35})
+    verify_qlinearleakyrelu([5, 1, 4, 6], {"alpha": 0.65})
+
+
 @tvm.testing.parametrize_targets
 def test_qlinearsigmoid(target, dev):
     def verify_qlinearsigmoid(a_shape):