Function dequant_to_bf16 

pub fn dequant_to_bf16(
    t: GgmlType,
    block_bytes: &[u8],
    n_elements: usize,
    out: &mut [u16],
) -> Result<()>

Dequantize into BF16 bit patterns (round-to-nearest-even), the form the GGUF loader hands to WeightTensor { dtype: BF16 }. Goes via f32 for a single, obviously-correct code path.