mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-11-13 02:17:13 +08:00
51 lines
1.7 KiB
Python
51 lines
1.7 KiB
Python
# 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.
|
|
|
|
"""Quantized Linear."""
|
|
|
|
import torch.nn as nn
|
|
|
|
from ... import tensor_quant
|
|
from .quant_module import QuantLinearConvBase, QuantModuleRegistry, _LegacyQuantLinearConvBaseMixin
|
|
|
|
__all__ = ["Linear", "QuantLinear"]
|
|
|
|
|
|
@QuantModuleRegistry.register({nn.Linear: "nn.Linear"})
|
|
class _QuantLinear(QuantLinearConvBase):
|
|
"""Quantized base class for nn.Linear type classes."""
|
|
|
|
default_quant_desc_weight = tensor_quant.QUANT_DESC_8BIT_LINEAR_WEIGHT_PER_ROW
|
|
|
|
@staticmethod
|
|
def quantized_linear_fn(package, func_name, self, input, weight, *args, **kwargs):
|
|
"""Quantized version of a generic linear functional."""
|
|
output = getattr(package, func_name)(
|
|
self.input_quantizer(input),
|
|
self.weight_quantizer(weight),
|
|
*args,
|
|
**kwargs,
|
|
)
|
|
return self.output_quantizer(output)
|
|
|
|
|
|
class QuantLinear(_LegacyQuantLinearConvBaseMixin, nn.Linear):
|
|
"""Quantized version of nn.Linear."""
|
|
|
|
default_quant_desc_weight = _QuantLinear.default_quant_desc_weight
|
|
|
|
|
|
Linear = QuantLinear
|