mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
250d9c293d
* Update TensorRT-LLM --------- Co-authored-by: Bhuvanesh Sridharan <bhuvan.sridharan@gmail.com> Co-authored-by: Morgan Funtowicz <funtowiczmo@gmail.com> Co-authored-by: Eddie-Wang1120 <wangjinheng1120@163.com> Co-authored-by: meghagarwal <16129366+megha95@users.noreply.github.com>
27 lines
1016 B
Python
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',
|
|
]
|