pub fn decode_batch(
spec: &ModelSpec,
dir: &str,
ctx: usize,
seqs: &[(usize, usize)],
) -> AuthoredExpand description
B DECODE STEPS AT ONCE: sequence b brings token tok_b at position pos_b (1-based) and its own carried
state, and every sequence emits its own next token. The hidden states are stacked into a B × d matrix and
everything that reads a weight runs on the stack; what depends on one sequence’s position or state runs per
sequence, on that sequence’s row, exactly as the single step writes it.