diff --git a/common/common.cpp b/common/common.cpp
index 17a0c7ce..1ffe67e3 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -1240,10 +1240,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
             params.split_mode = LLAMA_SPLIT_MODE_LAYER;
         }
         else if (arg_next == "row") {
-#ifdef GGML_USE_SYCL
-            fprintf(stderr, "warning: The split mode value:[row] is not supported by llama.cpp with SYCL. It's developing.\nExit!\n");
-            exit(1);
-#endif // GGML_USE_SYCL
+            fprintf(stderr, "\n\n=====================================================================================\n");
+            fprintf(stderr, " Split mode row is no longer supported\n");
+            fprintf(stderr, "=====================================================================================\n\n\n");
+            GGML_ABORT("fatal error");
             params.split_mode = LLAMA_SPLIT_MODE_ROW;
         }
         else {
@@ -2217,8 +2217,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
         options.push_back({ "*",           "-sm,   --split-mode SPLIT_MODE",
                                                                         "how to split the model across multiple GPUs, one of:\n"
                                                                         "  - none: use one GPU only\n"
-                                                                        "  - layer (default): split layers and KV across GPUs\n"
-                                                                        "  - row: split rows across GPUs" });
+                                                                        "  - layer (default): split layers and KV across GPUs\n" });
         options.push_back({ "*",           "-ts,   --tensor-split SPLIT",
                                                                         "fraction of the model to offload to each GPU, comma-separated list of proportions, e.g. 3,1" });
         options.push_back({ "*",           "-dev,   --device dev1,dev2",
diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp
index ed859e31..a479ba39 100644
--- a/examples/llama-bench/llama-bench.cpp
+++ b/examples/llama-bench/llama-bench.cpp
@@ -334,7 +334,7 @@ static void print_usage(int /* argc */, char ** argv) {
     printf("  -ngl, --n-gpu-layers <n>            (default: %s)\n", join(cmd_params_defaults.n_gpu_layers, ",").c_str());
     printf("  --n-cpu-moe <n>                     (default: none)\n");
     printf("  -rpc, --rpc <rpc_servers>           (default: %s)\n", join(cmd_params_defaults.rpc_servers, ",").c_str());
-    printf("  -sm, --split-mode <none|layer|row>  (default: %s)\n", join(transform_to_str(cmd_params_defaults.split_mode, split_mode_str), ",").c_str());
+    printf("  -sm, --split-mode <none|layer>      (default: %s)\n", join(transform_to_str(cmd_params_defaults.split_mode, split_mode_str), ",").c_str());
     printf("  -mg, --main-gpu <i>                 (default: %s)\n", join(cmd_params_defaults.main_gpu, ",").c_str());
     printf("  -nkvo, --no-kv-offload <0|1>        (default: %s)\n", join(cmd_params_defaults.no_kv_offload, ",").c_str());
     printf("  -fa, --flash-attn <0|1>             (default: %s)\n", join(cmd_params_defaults.flash_attn, ",").c_str());
@@ -631,7 +631,11 @@ static cmd_params parse_cmd_params(int argc, char ** argv) {
                 } else if (m == "layer") {
                     mode = LLAMA_SPLIT_MODE_LAYER;
                 } else if (m == "row") {
-                    mode = LLAMA_SPLIT_MODE_ROW;
+                    fprintf(stderr, "\n\n=======================================================================\n");
+                    fprintf(stderr, "Split mode 'row' is no longer supported\n");
+                    fprintf(stderr, "=======================================================================\n\n\n");
+                    invalid_param = true;
+                    break;
                 } else {
                     invalid_param = true;
                     break;