--- a/source/backend/cuda/execution/weight_only_quant/ConvFpAIntBExecution.cu +++ b/source/backend/cuda/execution/weight_only_quant/ConvFpAIntBExecution.cu @@ -1792,7 +1792,8 @@ DivModFast d_ow(ow); DivModFast d_oh(oh); - const int batch = inputs[0]->batch(); + // Pointwise convolution has one GEMM row per spatial position, not only per batch item. + const int batch = mGemmInfo.elh[0]; // Weight dequantization now happens once in onResize (STATIC buffer). // GEMV path (batch <= 4) reads packed INT4 weights directly.