PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
# Copyright (c) 2026 Intel Corporation
#
# 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.
# NOTE: hpu_patch must be imported before any module that triggers loading of
# `transformers.modeling_utils` (e.g. `fp8_quant`), otherwise the upstream
# `transformers.integrations.finegrained_fp8` module is loaded without the
# HPU-compatible overrides.
from . import hpu_patch as _hpu_patch
from .fp8_quant import *