LayerNorm conversion error

Hi, In the latest version of TinyNeuralNetwork layer norm causes the conversion to fail.

error output:
```
Error in QNNPACK: failed to create add operator with 8.124962e-06 A-to-output scale ratio: scale ratio must be in [2**-14, 2**8) range
...
File "../TinyNeuralNetwork/tinynn/graph/quantization/modules.py", line 136, in forward
return self.f_add_2.add(norm_alpha, bias_fq_expand)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "../torch/ao/nn/quantized/modules/functional_modules.py", line 241, in add
r = ops.quantized.add(x, y, scale=self.scale, zero_point=self.zero_point)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "../torch/_ops.py", line 1116, in __call__
return self._op(*args, **(kwargs or {}))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: createStatus == pytorch_qnnp_status_success INTERNAL ASSERT FAILED at "../aten/src/ATen/native/quantized/cpu/BinaryOps.cpp":204, please report a bug to PyTorch. failed to create QNNPACK Add operator
```

torch version: 2.5.1
python version: 3.12

This should reproduce it:
```python
import torch.nn as nn
import torch
from tinynn.graph.quantization.quantizer import PostQuantizer
from tinynn.converter import TFLiteConverter
from tinynn.graph.tracer import model_tracer

class LayerNormModel(nn.Module):

def __init__(self,):
super().__init__()
self.layer_norm = torch.nn.LayerNorm(256)

def forward(self, x: torch.Tensor):
return self.layer_norm(x)

def _main():
dummy_input = torch.rand(1, 60, 256).float()
model = LayerNormModel()
qat_config = {
"backend": "qnnpack",
"per_tensor": True,
"disable_requantization_for_cat": True,
}
with model_tracer():
quantizer = PostQuantizer(
model, (dummy_input), work_dir="LayerNormModel", config=qat_config
)

layer_norm_model = quantizer.quantize()

layer_norm_model(dummy_input)

with torch.no_grad():
layer_norm_model.eval()
layer_norm_model.cpu()

layer_norm_model = quantizer.convert(layer_norm_model)
torch.backends.quantized.engine = quantizer.backend
converter = TFLiteConverter(
layer_norm_model,
(dummy_input),
"layer_norm.tflite",
fuse_quant_dequant=True,
quantize_target_type="int8"
)
converter.convert()

if __name__ == '__main__':
_main()
```

Is there a new flag or something I should set to make this work?

Run the supplied LayerNormModel reproduction with torch 2.5.1 and Python 3.12, then inspect tinynn/graph/quantization/modules.py at the reported forward call and the PostQuantizer conversion path. Trace the QNNPACK scale-ratio failure through quantization and conversion. Done means the example converts to layer_norm.tflite without the QNNPACK error, with coverage for this LayerNorm case.

Written by the indexing model from the issue text.