Method set_logits

common/sampling.cpp:130–162

    }

    void set_logits(struct llama_context * ctx, int idx) {
        const float *       sampled_probs  = llama_get_sampled_probs_ith     (ctx, idx);
        const float *       sampled_logits = llama_get_sampled_logits_ith    (ctx, idx);
        const llama_token * sampled_ids    = llama_get_sampled_candidates_ith(ctx, idx);

        const llama_model * model = llama_get_model(ctx);
        const llama_vocab * vocab = llama_model_get_vocab(model);

        const int n_vocab = llama_vocab_n_tokens(vocab);

        if (sampled_probs) {
            const uint32_t sampled_probs_count = llama_get_sampled_probs_count_ith(ctx, idx);
            cur.resize(sampled_probs_count);
            for (uint32_t i = 0; i < sampled_probs_count; ++i) {
                cur[i] = llama_token_data{sampled_ids[i], sampled_logits[i], sampled_probs[i]};
            }
        } else if (sampled_logits) {
            const uint32_t sampled_logits_count = llama_get_sampled_logits_count_ith(ctx, idx);
            cur.resize(sampled_logits_count);
            for (uint32_t i = 0; i < sampled_logits_count; i++) {
                cur[i] = llama_token_data{sampled_ids[i], sampled_logits[i], 0.0f};
            }
        } else {
            const auto * logits = llama_get_logits_ith(ctx, idx);
            GGML_ASSERT(logits != nullptr);
            cur.resize(n_vocab);
            for (llama_token token_id = 0; token_id < n_vocab; token_id++) {
                cur[token_id] = llama_token_data{token_id, logits[token_id], 0.0f};
            }
        }

        cur_p = { cur.data(), cur.size(), -1, false };
    }

    common_time_meas tm() {
        return common_time_meas(t_total_us, params.no_perf);