ggml: fix CUDA grid launch condition for large block_nums.y in binbcast (#16742)

* Fix CUDA grid launch condition for large block_nums.y

* add backend ops test

* reduce test  repetitions

ggml/src/ggml-cuda/binbcast.cu

@@ -272,7 +272,7 @@ static void launch_bin_bcast_pack(const ggml_tensor * src0, const ggml_tensor *
         const uint3 ne12 = init_fastdiv_values((uint32_t) cne1[2]);
         const uint3 ne13 = init_fastdiv_values((uint32_t) cne1[3]);
 
-        if (block_nums.z > 65535) {
+        if (block_nums.z > 65535 || block_nums.y > 65535) {
             int         block_num  = (ne0 * ne1 * ne2 * ne3 + block_size - 1) / block_size;
             const uint3 prod_012    = init_fastdiv_values((uint32_t) (ne0 * ne1 * ne2));
             const uint3 prod_01     = init_fastdiv_values((uint32_t) (ne0 * ne1));

tests/test-backend-ops.cpp

@@ -6407,6 +6407,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
         add_test_bin_bcast(type, {1, 1, 640, 1}, {32, 32, 1, 1});
         add_test_bin_bcast(type, {5120, 1, 1, 1}, {1, 256, 1, 1});
         add_test_bin_bcast(type, {640, 1, 1, 1}, {1, 1, 1, 1});
+        add_test_bin_bcast(type, {64, 262144, 1, 1}, {1, 1, 1, 1});
         //add_test_bin_bcast(type, {3, 3, 2560, 1280}, {1, 1, 1, 1});
         //add_test_bin_bcast(type, {3, 3, 2560, 1280}, {2, 1, 1, 1});
     }