cuda : do not use dmmv if the tensor does not have enough cols

Author: slaren

ggml/src/ggml-cuda.cu

@@ -1875,7 +1875,8 @@ static void ggml_cuda_mul_mat(ggml_backend_cuda_context & ctx, const ggml_tensor
 
     bool use_dequantize_mul_mat_vec = (ggml_is_quantized(src0->type) || src0->type == GGML_TYPE_F16)
         && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
-        && src0->ne[0] % GGML_CUDA_DMMV_X == 0 && src1->ne[1] == 1;
+        && src0->ne[0] % GGML_CUDA_DMMV_X == 0 && src0->ne[0] >= GGML_CUDA_DMMV_X*2
+        && src1->ne[1] == 1;
     bool          use_mul_mat_vec_q =  ggml_is_quantized(src0->type)
         && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
         && src1->ne[1] <= MMVQ_MAX_BATCH_SIZE;