mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-23 08:08:52 -04:00
static_assert(nwarps*tile_C::I == mmq_y) locks nwarps=8 for mmq_y=128; can't raise occupancy without co-scaling mmq_y (blows Blackwell smem). MMQ kernel is not freely tunable -> parity needs the tcgen05/CUTLASS rewrite, not knobs. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>