Class ggml_context

tests/test_metal_conv_dw.cpp:29–29

    size_t ctx_size = ggml_tensor_overhead() * 16 + ggml_graph_overhead();
    struct ggml_init_params params = {ctx_size, nullptr, true};
    struct ggml_context* ctx = ggml_init(params);

    // Kernel: [KW, KH, 1, C]
    auto* knl = ggml_new_tensor_4d(ctx, GGML_TYPE_F32, KW, KH, 1, C);