Files
FastDeploy/fastdeploy/input/mm_data_processor.py
T
kevin d60daca4a8 [Feature] consider multimodal model when dummy run (#6045)
* add mm do profile

* updata code

* update code

* update code

* update code

* update test case

* update code

* update code

* fix xpu bug

* update code

* add mm do profile

* update test case

* update code
2026-02-09 17:49:55 +08:00

56 lines
1.4 KiB
Python

"""
# 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.
"""
from abc import ABC, abstractmethod
class MMBaseDataProcessor(ABC):
def __init__(
self,
**kwargs,
) -> None:
"""
Initialize the mm data processor.
"""
@staticmethod
@abstractmethod
def mm_num_tokens(grid_thw: list) -> int:
"""
Calculate the number of tokens in the multimodal input.
"""
raise NotImplementedError
def get_max_image_tokens(self, *args, **kwargs) -> int:
"""
Get the maximum number of image tokens.
"""
return 0
def get_max_video_tokens(self, *args, **kwargs) -> int:
"""
Get the maximum number of video tokens.
"""
return 0
def get_max_audio_tokens(self, *args, **kwargs) -> int:
"""
Get the maximum number of audio tokens.
"""
return 0