Skip to main content

blockscaled_gemm_dequant

logicaffeine_compile::codegen_cuda::matrix

Function blockscaled_gemm_dequant 

Source 
pub fn blockscaled_gemm_dequant(
    m: usize,
    k: usize,
    n: usize,
    wq: &[i32],
    ws: &[f32],
    aq: &[i32],
    as_: &[f32],
) -> Vec<f64>
Expand description

GROUND TRUTH (f64): dequantize every element (q * scale) then multiply-accumulate. The unambiguous meaning of a Q8_0 matmul, order-independent.