forked from NVIDIA/TensorRT-LLM
-
Notifications
You must be signed in to change notification settings - Fork 0
/
cast.py
29 lines (25 loc) · 1.15 KB
/
cast.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
# SPDX-FileCopyrightText: Copyright (c) 2022-2023 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 ..functional import cast
from ..module import Module
class Cast(Module):
def __init__(self, output_dtype: str = 'float32') -> None:
super().__init__()
assert output_dtype in ('float32', 'float16', 'bfloat16', 'bool',
'int32', 'int8'), TypeError(
"%s is not supported" % output_dtype)
self.output_dtype = output_dtype
def forward(self, x):
return cast(x, self.output_dtype)