# Copyright (c) 2025 PaddlePaddle Authors. All Rights Reserved.
#
# 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.

import paddle
import paddlenlp_ops

weight = paddle.randn([10, 10], dtype="float16")

output, scale = paddlenlp_ops.weight_quantize_xpu(weight, algo="weight_only_int4", arch=-1, group_size=-1)
print("scale: ", scale)
print("output: ", output)

import pdb

pdb.set_trace()
p = 1