shard_dense_1d_bf16

Function shard_dense_1d_bf16 

Source
pub fn shard_dense_1d_bf16(
    src: DevicePtr,
    dim: usize,
    tp_rank: usize,
    tp_size: usize,
    gpu: &dyn GpuBackend,
) -> Result<(DevicePtr, usize)>
Expand description

2026-09-25: Shard a 1D BF16 vector [dim] on dim 0, for per-output vectors of column-parallel GEMMs. Same ownership rule as shard_dense_bf16.