torch.compile (inductor)

import torch
import torch.nn as nn

class Model(nn.Module):
    """
    A model implementing the pattern "Matmul_AvgPool_GELU_Scale_Max".
    """
    def __init__(self, in_features, out_features, pool_kernel_size, scale_factor):
        super(Model, self).__init__()
        self.matmul = nn.Linear(in_features, out_features)
        self.avg_pool = nn.AvgPool1d(kernel_size=pool_kernel_size)
        self.scale_factor = scale_factor

    def forward(self, x):
        """
        Args:
            x (torch.Tensor): Input tensor of shape (batch_size, in_features).

        Returns:
            torch.Tensor: Output tensor of shape (batch_size, out_features).
        """
        x = self.matmul(x)
        x = self.avg_pool(x.unsqueeze(1)).squeeze(1)
        x = torch.nn.functional.gelu(x)
        x = x * self.scale_factor
        x = torch.max(x, dim=1).values
        return x

batch_size = 1024
in_features = 8192
out_features = 8192
pool_kernel_size = 16
scale_factor = 2.0

def get_inputs():
    return [torch.rand(batch_size, in_features)]

def get_init_inputs():
    return [in_features, out_features, pool_kernel_size, scale_factor]