Enhanced python_backend autocomplete (#6504)

* Added testing for python_backend autocomplete: optional input and model_transaction_policy

qa/L0_model_config/autofill_noplatform/python/model_transaction_policy_invalid_args/config.pbtxt

@@ -0,0 +1,24 @@
+input [
+  {
+    name: "INPUT0"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  },
+  {
+    name: "INPUT1"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  }
+]
+output [
+  {
+    name: "OUTPUT0"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  },
+  {
+    name: "OUTPUT1"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  }
+]

qa/L0_model_config/autofill_noplatform/python/model_transaction_policy_invalid_args/expected

@@ -0,0 +1 @@
+model transaction property in auto-complete-config function for model 'model_transaction_policy_invalid_args' contains property other than 'decoupled'

qa/L0_model_config/autofill_noplatform/python/model_transaction_policy_invalid_args/model.py

@@ -0,0 +1,47 @@
+# Copyright 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#  * Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+#  * Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#  * Neither the name of NVIDIA CORPORATION nor the names of its
+#    contributors may be used to endorse or promote products derived
+#    from this software without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
+# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
+# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+
+class TritonPythonModel:
+    @staticmethod
+    def auto_complete_config(auto_complete_model_config):
+        input0 = {"name": "INPUT0", "data_type": "TYPE_FP32", "dims": [4]}
+        input1 = {"name": "INPUT1", "data_type": "TYPE_FP32", "dims": [4]}
+        output0 = {"name": "OUTPUT0", "data_type": "TYPE_FP32", "dims": [4]}
+        output1 = {"name": "OUTPUT1", "data_type": "TYPE_FP32", "dims": [4]}
+        transaction_policy = {"invalid": "argument"}
+
+        auto_complete_model_config.set_max_batch_size(4)
+        auto_complete_model_config.set_model_transaction_policy(transaction_policy)
+        auto_complete_model_config.add_input(input0)
+        auto_complete_model_config.add_input(input1)
+        auto_complete_model_config.add_output(output0)
+        auto_complete_model_config.add_output(output1)
+
+        return auto_complete_model_config
+
+    def execute(self, requests):
+        pass

qa/L0_model_config/autofill_noplatform/python/model_transaction_policy_mismatch/config.pbtxt

@@ -0,0 +1,28 @@
+model_transaction_policy {
+  decoupled: false
+}
+
+input [
+  {
+    name: "INPUT0"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  },
+  {
+    name: "INPUT1"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  }
+]
+output [
+  {
+    name: "OUTPUT0"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  },
+  {
+    name: "OUTPUT1"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  }
+]

qa/L0_model_config/autofill_noplatform/python/model_transaction_policy_mismatch/expected

@@ -0,0 +1 @@
+trying to change decoupled property in auto-complete-config for model 'model_transaction_policy_mismatch', which is already set to 'False'

qa/L0_model_config/autofill_noplatform/python/model_transaction_policy_mismatch/model.py

@@ -0,0 +1,46 @@
+# Copyright 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+#  * Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+#  * Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#  * Neither the name of NVIDIA CORPORATION nor the names of its
+#    contributors may be used to endorse or promote products derived
+#    from this software without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
+# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
+# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+
+class TritonPythonModel:
+    @staticmethod
+    def auto_complete_config(auto_complete_model_config):
+        input0 = {"name": "INPUT0", "data_type": "TYPE_FP32", "dims": [4]}
+        input1 = {"name": "INPUT1", "data_type": "TYPE_FP32", "dims": [4]}
+        output0 = {"name": "OUTPUT0", "data_type": "TYPE_FP32", "dims": [4]}
+        output1 = {"name": "OUTPUT1", "data_type": "TYPE_FP32", "dims": [4]}
+
+        auto_complete_model_config.set_max_batch_size(4)
+        auto_complete_model_config.set_model_transaction_policy(dict(decoupled=True))
+        auto_complete_model_config.add_input(input0)
+        auto_complete_model_config.add_input(input1)
+        auto_complete_model_config.add_output(output0)
+        auto_complete_model_config.add_output(output1)
+
+        return auto_complete_model_config
+
+    def execute(self, requests):
+        pass

qa/L0_model_config/autofill_noplatform_success/python/model_transaction_policy/config.pbtxt

@@ -0,0 +1,24 @@
+input [
+  {
+    name: "INPUT0"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  },
+  {
+    name: "INPUT1"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  }
+]
+output [
+  {
+    name: "OUTPUT0"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  },
+  {
+    name: "OUTPUT1"
+    data_type: TYPE_FP32
+    dims: [ 4 ]
+  }
+]

qa/L0_model_config/autofill_noplatform_success/python/model_transaction_policy/expected

@@ -0,0 +1,46 @@
+name: "model_transaction_policy"
+version_policy {
+  latest {
+    num_versions: 1
+  }
+}
+max_batch_size: 4
+input {
+  name: "INPUT0"
+  data_type: TYPE_FP32
+  dims: 4
+}
+input {
+  name: "INPUT1"
+  data_type: TYPE_FP32
+  dims: 4
+}
+output {
+  name: "OUTPUT0"
+  data_type: TYPE_FP32
+  dims: 4
+}
+output {
+  name: "OUTPUT1"
+  data_type: TYPE_FP32
+  dims: 4
+}
+instance_group {
+  name: "model_transaction_policy"
+  count: 1
+  gpus: 0
+  kind: KIND_GPU
+}
+default_model_filename: "model.py"
+optimization {
+  input_pinned_memory {
+    enable: true
+  }
+  output_pinned_memory {
+    enable: true
+  }
+}
+backend: "python"
+model_transaction_policy {
+  decoupled: true
+}

qa/L0_model_config/autofill_noplatform_success/python/model_transaction_policy/expected.1

@@ -0,0 +1,46 @@
+name: "model_transaction_policy"
+version_policy {
+  latest {
+    num_versions: 1
+  }
+}
+max_batch_size: 4
+input {
+  name: "INPUT1"
+  data_type: TYPE_FP32
+  dims: 4
+}
+input {
+  name: "INPUT0"
+  data_type: TYPE_FP32
+  dims: 4
+}
+output {
+  name: "OUTPUT0"
+  data_type: TYPE_FP32
+  dims: 4
+}
+output {
+  name: "OUTPUT1"
+  data_type: TYPE_FP32
+  dims: 4
+}
+instance_group {
+  name: "model_transaction_policy"
+  count: 1
+  gpus: 0
+  kind: KIND_GPU
+}
+default_model_filename: "model.py"
+optimization {
+  input_pinned_memory {
+    enable: true
+  }
+  output_pinned_memory {
+    enable: true
+  }
+}
+backend: "python"
+model_transaction_policy {
+  decoupled: true
+}

qa/L0_model_config/autofill_noplatform_success/python/model_transaction_policy/expected.2

@@ -0,0 +1,46 @@
+name: "model_transaction_policy"
+version_policy {
+  latest {
+    num_versions: 1
+  }
+}
+max_batch_size: 4
+input {
+  name: "INPUT0"
+  data_type: TYPE_FP32
+  dims: 4
+}
+input {
+  name: "INPUT1"
+  data_type: TYPE_FP32
+  dims: 4
+}
+output {
+  name: "OUTPUT1"
+  data_type: TYPE_FP32
+  dims: 4
+}
+output {
+  name: "OUTPUT0"
+  data_type: TYPE_FP32
+  dims: 4
+}
+instance_group {
+  name: "model_transaction_policy"
+  count: 1
+  gpus: 0
+  kind: KIND_GPU
+}
+default_model_filename: "model.py"
+optimization {
+  input_pinned_memory {
+    enable: true
+  }
+  output_pinned_memory {
+    enable: true
+  }
+}
+backend: "python"
+model_transaction_policy {
+  decoupled: true
+}

qa/L0_model_config/autofill_noplatform_success/python/model_transaction_policy/expected.3

@@ -0,0 +1,46 @@
+name: "model_transaction_policy"
+version_policy {
+  latest {
+    num_versions: 1
+  }
+}
+max_batch_size: 4
+input {
+  name: "INPUT1"
+  data_type: TYPE_FP32
+  dims: 4
+}
+input {
+  name: "INPUT0"
+  data_type: TYPE_FP32
+  dims: 4
+}
+output {
+  name: "OUTPUT1"
+  data_type: TYPE_FP32
+  dims: 4
+}
+output {
+  name: "OUTPUT0"
+  data_type: TYPE_FP32
+  dims: 4
+}
+instance_group {
+  name: "model_transaction_policy"
+  count: 1
+  gpus: 0
+  kind: KIND_GPU
+}
+default_model_filename: "model.py"
+optimization {
+  input_pinned_memory {
+    enable: true
+  }
+  output_pinned_memory {
+    enable: true
+  }
+}
+backend: "python"
+model_transaction_policy {
+  decoupled: true
+}