tiny.simd.matVecBFloatF32Add

1pub fn computeBFloatF32Add(2    comptime D: type,3    matrix: []const bfloat.BFloat16,4    vector: []const f32,5    add: []const f32,6    output: []f32,7) void {8    std.debug.assert(add.len >= output.len);9    computeBFloatF32(D, matrix, vector, output);10    for (output, add[0..output.len]) |*result, addend| result.* += addend;11}

1pub const matVecBFloatF32Add = matvec.computeBFloatF32Add;