Integrate Automated QDQ placement tool - part 3

Signed-off-by: Will Guo <willg@nvidia.com>

Author: willg-nv

modelopt/onnx/quantization/autotune/__init__.py

@@ -0,0 +1,61 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Pattern-based Q/DQ autotuning for ONNX models.
+
+Optimizes Q/DQ node placement in ONNX graphs to minimize TensorRT inference latency
+using hierarchical region analysis and pattern-based scheme reuse.
+"""
+
+from modelopt.onnx.quantization.autotune.common import (
+    AutotunerError,
+    AutotunerNotInitializedError,
+    Config,
+    InsertionScheme,
+    InvalidSchemeError,
+    PatternCache,
+    PatternSchemes,
+    Region,
+    RegionError,
+    RegionType,
+)
+
+from .insertion_points import (
+    ChildRegionInputInsertionPoint,
+    NodeInputInsertionPoint,
+    RegionOutputInsertionPoint,
+    ResolvedInsertionPoint,
+)
+from .region_pattern import RegionPattern
+from .region_search import CombinedRegionSearch
+
+__all__ = [
+    "AutotunerError",
+    "AutotunerNotInitializedError",
+    "ChildRegionInputInsertionPoint",
+    "CombinedRegionSearch",
+    "Config",
+    "InsertionScheme",
+    "InvalidSchemeError",
+    "NodeInputInsertionPoint",
+    "PatternCache",
+    "PatternSchemes",
+    "Region",
+    "RegionError",
+    "RegionOutputInsertionPoint",
+    "RegionPattern",
+    "RegionType",
+    "ResolvedInsertionPoint",
+]

modelopt/onnx/quantization/autotune/__main__.py

@@ -0,0 +1,24 @@
+#!/usr/bin/env python3
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Command-line interface for ONNX Q/DQ autotuning."""
+
+import sys
+
+from modelopt.onnx.quantization.autotune.cli import run_autotune
+
+if __name__ == "__main__":
+    sys.exit(run_autotune())