reorganize sparsity module to separate weight and attention sparsity

Signed-off-by: Kai Xu <[email protected]>

Author: kaix-nv

modelopt/torch/sparsity/__init__.py

@@ -13,7 +13,12 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-"""API for sparsification algorithms."""
+"""API for sparsification algorithms.
 
-from . import mode, module, plugins
-from .sparsification import *
+This module provides access to both weight sparsity and attention sparsity algorithms.
+For backward compatibility, weight sparsity APIs are re-exported at the module level.
+"""
+
+# Import weight sparsity for backward compatibility
+from .weight_sparsity import mode, module, plugins
+from .weight_sparsity.sparsification import *

modelopt/torch/sparsity/weight_sparsity/__init__.py

@@ -0,0 +1,23 @@
+# SPDX-FileCopyrightText: Copyright (c) 2024 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.
+
+"""API for weight sparsification algorithms."""
+
+from . import mode, module, plugins
+
+# Explicitly expose commonly used items
+from .mode import SparsityModeRegistry
+from .module import SparseModule, SpDMRegistry
+from .sparsification import *