Skip to main content

attn_shared_splits

Function attn_shared_splits 

Source
pub fn attn_shared_splits(span: usize, sms: usize) -> usize
Expand description

The most chunks lk_attention_shared cuts a row’s span of span positions into, the decode step’s in every form: one block a streaming multiprocessor (sms), its shared memory a block’s, and no more than give each chunk ATTN_MIN_SPLIT positions.