Method n_tokens

subprojects/llama.cpp/tools/server/server-task.cpp:1855–1863

}

size_t server_prompt_cache::n_tokens() const {
    size_t res = 0;

    for (const auto & state : states) {
        res += state.n_tokens();
    }

    return res;
}

server_prompt * server_prompt_cache::alloc(const server_prompt & prompt, size_t state_size) {
    // first check if the current state is contained fully in the cache