Function eval_tokens

examples/llava/llava-cli.cpp:13–27

#include <vector>

static bool eval_tokens(struct llama_context * ctx_llama, std::vector<llama_token> tokens, int n_batch, int * n_past) {
    int N = (int) tokens.size();
    for (int i = 0; i < N; i += n_batch) {
        int n_eval = (int) tokens.size() - i;
        if (n_eval > n_batch) {
            n_eval = n_batch;
        }
        if (llama_decode(ctx_llama, llama_batch_get_one(&tokens[i], n_eval, *n_past, 0))) {
            fprintf(stderr, "%s : failed to eval. token %d/%d (batch size %d, n_past %d)\n", __func__, i, N, n_batch, *n_past);
            return false;
        }
        *n_past += n_eval;
    }
    return true;
}

static bool eval_id(struct llama_context * ctx_llama, int id, int * n_past) {
    std::vector<llama_token> tokens;