From 45be2cd27a02f0fbe3354e9d07efc403b97da341 Mon Sep 17 00:00:00 2001 From: Michael Wand Date: Sat, 10 Jan 2026 01:16:07 -0800 Subject: [PATCH] Corrected: changed s13 = src1->nb[3] instead of nb[2] (llama/18724) --- 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 ceb95758..c9aa7024 100644 --- a/ggml/src/ggml-cuda/mmq.cu +++ b/ggml/src/ggml-cuda/mmq.cu @@ -190,7 +190,7 @@ void ggml_cuda_mul_mat_q( { const int64_t s11 = src1->nb[1] / ts_src1; const int64_t s12 = src1->nb[2] / ts_src1; - const int64_t s13 = src1->nb[2] / ts_src1; + const int64_t s13 = src1->nb[3] / ts_src1; if (use_native_mxfp4) { quantize_mmq_mxfp4_cuda(src1_d, ids_src1.get(), src1_q8_1.get(), src0->type, ne10, s11, s12, s13,