Per-tensor INT8 uses one scale for the whole matrix, so a single outlier ruins precision everywhere. Group-wise quantisation (as in GPTQ, AWQ and llama.cpp's Q4 formats) gives every group of, say, 32 consecutive weights in a row its own scale.
Unlock this and every premium problem across all tracks — plus hidden-test grading, advanced AI engineering modules and new content every week.
Start 7-day free trial