3 · Train a model you own · 24/38
FlashAttention
More arithmetic, faster — attention was HBM-bound.
playnaive writes N×N to HBM · Flash keeps tiles in SRAM · same math, fewer tripsAttention was HBM-bound. Tiles in SRAM → more arithmetic, faster.
Naive attention writes N×N to HBM. Flash keeps Br×Bc tiles in SRAM.