#
# Copyright (c) 2025 Huawei Technologies 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.
# This file is a part of the vllm-ascend project.
#

from typing import Optional, Tuple, Union

import torch


def torchair_rmsnorm_forward_oot(
    self,
    x: torch.Tensor,
    residual: Optional[torch.Tensor] = None,
) -> Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]]:
    """AscendRMSNorm forward in torchair mode.

    The key difference from the original implementation is the removal of operators
    from the torch.ops.vllm class, as these operators only function in non-torchair
    modes. Adding them back would cause the graph compilation to fail.
    """

    import torch_npu

    from vllm_ascend.utils import is_310p
    if residual is not None:
        if is_310p():
            orig_dtype = residual.dtype
            x = x + residual.to(x.dtype)
            residual = x.to(orig_dtype)
            x, _ = torch_npu.npu_rms_norm(x, self.weight,
                                          self.variance_epsilon)
        else:
            x, _, residual = torch_npu.npu_add_rms_norm(
                x, residual, self.weight, self.variance_epsilon)
        return x, residual

    x, residual = torch_npu.npu_rms_norm(x, self.weight, self.variance_epsilon)
    return x