Why architecture matters here
GPTQ fails on wrong calibration or too aggressive bits. Architecture matters because Hessian + column order + groups compose.
Advertisement
The architecture: every piece explained
The top strip is math. Calibration set. Layer input. Hessian H. Cholesky.
The middle row is algorithm. Column-wise quant. Error redistribute. 4-bit weights. Accuracy check.
The lower rows are ops. Group size. Metrics. Ops — calibration + kernel + serving.
Advertisement
End-to-end flow
End-to-end: load FP16 model. Pass 128 calibration samples. Per layer, compute H = X^T X. Cholesky-invert. Quantize column j, compute residual, redistribute to columns > j using H^-1 row. Repeat. Group size 128 lets scales adapt.