pub fn shard_gdn_value_vector(
src: DevicePtr,
dims: &TpGdnDims,
unit: usize,
elem_bytes: usize,
gpu: &dyn GpuBackend,
) -> Result<(DevicePtr, usize)>Expand description
2026-09-25: Shard a per-value-head 1D vector on the value-head axis:
[full_nv * unit] → [local_nv * unit], where unit is the number of
elements per value head and elem_bytes their size. The loaders call it for
a_log / dt_bias (unit = 1, elem_bytes = 4). Returns
(ptr, local_len_elems).