pub fn fp8_grouped_active_cap(
num_tokens: u32,
top_k: u32,
num_experts: u32,
) -> u32Expand description
2026-09-25: Cap on active experts, which sizes the grouped grids’ Y extent:
num_tokens * top_k rows can reach at most that many distinct experts. It
does not depend on the routing, so a captured graph stays valid for every
routing.