Function fp8_vector_dequantize 

pub fn fp8_vector_dequantize(
    weight: &Tensor,
    inv_scales: &Tensor,
    out_ty: DType,
) -> Result<Tensor>

FP8 vector dequantize.

• Expects weight to be fp8
• Expects inv_scales to be f32
• weight * inv_scale = dequantized