Clarification regarding the readme example

```py
from comfy_kitchen.tensor import QuantizedTensor, TensorCoreFP8Layout, TensorCoreNVFP4Layout

# Quantize a tensor
x = torch.randn(128, 256, device="cuda", dtype=torch.bfloat16)
qt = QuantizedTensor.from_float(x, TensorCoreFP8Layout)

# Operations dispatch to optimized kernels automatically
output = torch.nn.functional.linear(qt, weight_qt)

# Dequantize back to float
dq = qt.dequantize()
```

How is `weight_qt` computed in this case?

Also, is it recommended to quantize the input (which seems to be `qt` in this case) instead of the weights?

Start by reviewing the README example and the QuantizedTensor.from_float, TensorCoreFP8Layout, and dequantize entry points mentioned in the issue. Clarify how weight_qt is obtained and document the recommended choice between quantizing inputs and weights; the README should answer both questions directly.

Written by the indexing model from the issue text.