Tile Q and K/V blocks so scores never materialize globally. Maintain each query row’s running maximum and normalization sum, rescaling the accumulated output when a new tile changes the maximum.
Test empty input, one-element input, duplicates, boundary indices, invalid states, and the largest allowed size; state time and space complexity.
Get asked follow-ups live, then receive a scored report — like a real MLE interview loop.
Start AI mock interview