OpenVINO backend: fix accurace issue in gemma3n arch test

Author: zhaixuejun1993

ggml/src/ggml-openvino/ggml-openvino.cpp

@@ -932,29 +932,6 @@ static bool is_op_unsupported_case(const ggml_tensor * op) {
         }
         break;
     }
-    case GGML_OP_DIV: {
-        bool requires_broadcast = false;
-        for (int i = 0; i < 4; i++) {
-            if (op->src[0]->ne[i] == op->src[1]->ne[i]) {
-                continue;
-            }
-
-            if (op->src[0]->ne[i] != 1 && op->src[1]->ne[i] != 1) {
-                return true;
-            }
-
-            requires_broadcast = true;
-        }
-
-        // The GPU plugin can fuse broadcast DIV into the preceding FFN GEMM path
-        // and produce infs for per-channel scale vectors. Keep those DIVs on CPU
-        // until the fused GPU kernel is reliable. (falied case llama-arch-test mpt)
-        if (requires_broadcast && ggml_openvino_get_device_name() == "GPU") {
-            return true;
-        }
-
-        break;
-    }
     case GGML_OP_SUM_ROWS: {
         // if the input is PERMUTE skip
         if (op->src[0]->op == GGML_OP_PERMUTE) {