From 0dce7f9128d94381d3812f8b8daa3d43ce4e3bda Mon Sep 17 00:00:00 2001 From: Iwan Kawrakow Date: Fri, 8 Aug 2025 11:18:26 +0300 Subject: [PATCH] Prevent assert with quantized K cache and no FA --- ggml/src/ggml-cuda.cu | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ggml/src/ggml-cuda.cu b/ggml/src/ggml-cuda.cu index 7fee71d8..67d9828c 100644 --- a/ggml/src/ggml-cuda.cu +++ b/ggml/src/ggml-cuda.cu @@ -1647,7 +1647,7 @@ static void ggml_cuda_op_mul_mat( } const int64_t src1_col_stride = split && used_devices > 1 ? MUL_MAT_SRC1_COL_STRIDE : ne11; - if (!(split && used_devices > 1) && quantization_done && ne11 == 1 && ne12 > 1 && ne13 == 1) { + if (!(split && used_devices > 1) && quantization_done && ne11 == 1 && ne12 > 1 && ne13 == 1 && ne02 == ne12 && ne02 == dst->ne[2]) { //printf("invoking fast path for %s x %s\n", src0->name, src1->name); int id = ctx.device; char * src0_dd_i = dev[id].src0_dd;