Function load_qk_norms_tp 

pub fn load_qk_norms_tp<F, T>(
    config: &ModelConfig,
    norm_loader: F,
) -> Result<(T, T)>
where
    F: FnMut(&str, usize) -> Result<T>,

Q/K-norm 1D shard pair. The closure receives (name, full_dim) and returns the loader’s sharded norm — typically a DenseWeight. q_norm is sharded against full_q_n; k_norm against full_kv_n. Returns (q_norm, k_norm).