Add unit-test for CUB-based mean

Tests should run with CUDA Graphs enabled per default on NVGPUs

Author: ORippler

tests/test-backend-ops.cpp

@@ -6006,6 +6006,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
     test_cases.emplace_back(new test_sum(GGML_TYPE_F32, { 33, 256, 1, 1 }));
     test_cases.emplace_back(new test_sum_rows(GGML_TYPE_F32, { 33, 256, 1, 1 }));
     test_cases.emplace_back(new test_mean(GGML_TYPE_F32, { 33, 256, 1, 1 }));
+    test_cases.emplace_back(new test_mean(GGML_TYPE_F32, { 32769, 1, 1, 1 }));
     test_cases.emplace_back(new test_group_norm(GGML_TYPE_F32, {64, 64, 320, 1}));
     test_cases.emplace_back(new test_group_norm(GGML_TYPE_F32, {9, 9, 1280, 1}));
     test_cases.emplace_back(new test_acc());