| # SPDX-FileCopyrightText: Copyright (c) 2025 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. | |
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| class MLP(nn.Module): | |
| def __init__( | |
| self, | |
| dim: int, | |
| hidden_dim: int, | |
| ): | |
| """ | |
| Initializes the multilayer perceptron (MLP) module. | |
| Args: | |
| dim: The input and output dimensionality. | |
| hidden_dim: The dimensionality of the hidden layer. | |
| """ | |
| super().__init__() | |
| self.w1 = nn.Linear(dim, hidden_dim, bias=False) | |
| self.w2 = nn.Linear(hidden_dim, dim, bias=False) | |
| self.w3 = nn.Linear(dim, hidden_dim, bias=False) | |
| def forward(self, x: torch.Tensor) -> torch.Tensor: | |
| """ | |
| Performs the forward pass of the MLP module. | |
| Args: | |
| x: The input tensor of shape (batch_size, dim). | |
| Returns: | |
| The output tensor of shape (batch_size, dim). | |
| """ | |
| output = self.w2(F.silu(self.w1(x)) * self.w3(x)) | |
| return output | |