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.