Function dequantize_tensor 

pub fn dequantize_tensor(
    quantized: &QuantizedTensor,
) -> QuantResult<Tensor<f32>>

Dequantizes a quantized tensor back to f32.

Arguments

• quantized - The quantized tensor to dequantize

Returns

A tensor with f32 values

Example

use axonml_quant::{quantize_tensor, dequantize_tensor, QuantType};

let tensor = Tensor::from_vec(vec![1.0, 2.0, 3.0, 4.0], &[4])?;
let quantized = quantize_tensor(&tensor, QuantType::Q8_0)?;
let dequantized = dequantize_tensor(&quantized)?;