Method graph_get_cb

subprojects/llama.cpp/src/llama-context.cpp:2144–2168

}

llm_graph_cb llama_context::graph_get_cb() const {
    return [&](const llama_ubatch & ubatch, ggml_tensor * cur, const char * name, int il) {
        if (il >= 0) {
            ggml_format_name(cur, "%s-%d", name, il);
        } else {
            ggml_set_name(cur, name);
        }

        // norm may be automatically assigned to the backend of the previous layer, increasing data transfer between backends
        // FIXME: fix in ggml_backend_sched
        const bool full_offload = model.n_gpu_layers() > model.hparams.n_layer;
        if (ubatch.n_tokens < 32 || full_offload) {
            if (il != -1 && strcmp(name, "norm") == 0) {
                const auto & dev_layer = model.dev_layer(il);
                for (const auto & backend : backends) {
                    if (ggml_backend_get_device(backend.get()) == dev_layer) {
                        if (ggml_backend_supports_op(backend.get(), cur)) {
                            ggml_backend_sched_set_tensor_backend(sched.get(), cur, backend.get());
                        }
                    }
                }
            }
        }
    };
}

//
// state save/load