mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
258c7540c0
Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com> open source f8c0381a2bc50ee2739c3d8c2be481b31e5f00bd (#2736) Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com> Add note for blackwell (#2742) Update the docs to workaround the extra-index-url issue (#2744) update README.md (#2751) Fix github io pages (#2761) Update
25 lines
1.1 KiB
Python
25 lines
1.1 KiB
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 . import utils
|
|
from .mode import (KV_CACHE_QUANT_ALGO_LIST, MODELOPT_FLOW_QUANTIZATIONS,
|
|
QUANT_ALGO_LIST, W8A8_SQ_PLUGIN_LIST, QuantAlgo, QuantMode)
|
|
from .quantize_by_modelopt import quantize_and_export, quantize_nemo_and_export
|
|
|
|
__all__ = [
|
|
'QUANT_ALGO_LIST', 'KV_CACHE_QUANT_ALGO_LIST', 'W8A8_SQ_PLUGIN_LIST',
|
|
'MODELOPT_FLOW_QUANTIZATIONS', 'QuantAlgo', 'QuantMode',
|
|
'quantize_and_export', 'quantize_nemo_and_export', 'utils'
|
|
]
|