TensorRT-LLMs/tensorrt_llm/quantization/__init__.py
石晓伟 850b6fa1e7
Update TensorRT-LLM (#1358)
Co-authored-by: Kaiyu <26294424+kaiyux@users.noreply.github.com>
2024-03-26 20:47:14 +08:00

27 lines
1016 B
Python

# SPDX-FileCopyrightText: Copyright (c) 2022-2024 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.
from .mode import (KV_CACHE_QUANT_ALGO_LIST, QUANT_ALGO_LIST,
W8A8_SQ_PLUGIN_LIST, QuantAlgo, QuantMode)
from .quantize_by_ammo import quantize_and_export
__all__ = [
'QUANT_ALGO_LIST',
'KV_CACHE_QUANT_ALGO_LIST',
'W8A8_SQ_PLUGIN_LIST',
'QuantAlgo',
'QuantMode',
'quantize_and_export',
]