From f747cbca081c08ce4ec6811b3f5df1b71f129b2a Mon Sep 17 00:00:00 2001 From: Iwan Kawrakow Date: Fri, 8 Aug 2025 13:42:03 +0300 Subject: [PATCH] Fix MMQ when running with quantized K cache without FA --- ggml/src/ggml-cuda/mmq.cu | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ggml/src/ggml-cuda/mmq.cu b/ggml/src/ggml-cuda/mmq.cu index a0e7da12..1e3accf0 100644 --- a/ggml/src/ggml-cuda/mmq.cu +++ b/ggml/src/ggml-cuda/mmq.cu @@ -14,7 +14,7 @@ void ggml_cuda_op_mul_mat_q( const int64_t src1_padded_row_size, cudaStream_t stream) { const int64_t ne00 = src0->ne[0]; - const int64_t nb01 = src0->nb[1]; + const int64_t nb01 = ggml_row_size(src0->type, ne00); const int64_t ne10 = src1->ne[0]; const int64_t ne11 = src1->ne[1];