Function quantize_tensor 

pub fn quantize_tensor(
    tensor: &Tensor<f32>,
    quant_type: QuantType,
) -> QuantResult<QuantizedTensor>

Quantizes a tensor to the specified quantization type.

Arguments

• tensor - The input tensor to quantize
• quant_type - The target quantization type

Returns

A quantized tensor

Example

use axonml_quant::{quantize_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)?;