Method graph_max_nodes

subprojects/llama.cpp/src/llama-context.cpp:2015–2024

//

uint32_t llama_context::graph_max_nodes(uint32_t n_tokens) const {
    if (model.arch == LLM_ARCH_QWEN3NEXT) {
        return std::max<uint32_t>(n_tokens * 40, 32u * model.n_tensors());
    }
    uint32_t res = std::max<uint32_t>(1024u, 8u*model.n_tensors());
    for (const auto & lora : model.loras) {
        res += lora->get_n_nodes();
    }
    return res;
}

llm_graph_result * llama_context::get_gf_res_reserve() const {
    return static_cast<llm_graph_result *>(gf_res_reserve.get());