################################################################################
# Copyright(c)2020-2025 Shanghai Biren Technology Co., Ltd. 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 typing import Optional

import torch
from fastcore.basics import patch_to

from vllm.model_executor.models.bert import BertModel
from vllm.sequence import IntermediateTensors


@patch_to(BertModel)
def forward(
    self,
    input_ids: torch.Tensor,
    positions: torch.Tensor,
    intermediate_tensors: Optional[IntermediateTensors] = None,
    inputs_embeds: Optional[torch.Tensor] = None,
) -> torch.Tensor:
    if inputs_embeds is not None:
        hidden_states = inputs_embeds
    else:
        input_ids = input_ids.unsqueeze(
            0
        )  # Note: set input batch size (bs) to 1 here; otherwise attention module will raise an error.
        hidden_states = self.embeddings(input_ids=input_ids,
                                        position_ids=positions)
        hidden_states = self.encoder(hidden_states).squeeze(0)
    return hidden_states