Skip to main content

tp_decode_batch

Function tp_decode_batch 

Source
pub fn tp_decode_batch(
    spec: &ModelSpec,
    dir: &str,
    ctx: usize,
    seqs: &[(usize, usize)],
    tp: usize,
) -> Result<TpAuthored, NotYet>
Expand description

A BATCHED decode step over tp chips — the serving shape: the stacked sequences with every layer split, the embedding and the head on the replicated spine.