Skip to main content

attn_i8_smem_bytes

Function attn_i8_smem_bytes 

Source
pub const fn attn_i8_smem_bytes(hd: usize, vd: usize) -> usize
Expand description

The two-word attention block’s dynamic shared memory: a tile’s keys’ and values’ two words, rows padded 16 bytes, and both its scales in two buffers.