Function llama_sample_top_p

llama.cpp:8194–8224

}

void llama_sample_top_p(struct llama_context * ctx, llama_token_data_array * candidates, float p, size_t min_keep) {
    if (p >= 1.0f) {
        return;
    }

    llama_sample_softmax(ctx, candidates);

    const int64_t t_start_sample_us = ggml_time_us();

    // Compute the cumulative probabilities
    float cum_sum = 0.0f;
    size_t last_idx = candidates->size;

    for (size_t i = 0; i < candidates->size; ++i) {
        cum_sum += candidates->data[i].p;

        // Check if the running sum is at least p or if we have kept at least min_keep tokens
        // we set the last index to i+1 to indicate that the current iterate should be included in the set
        if (cum_sum >= p && i + 1 >= min_keep) {
            last_idx = i + 1;
            break;
        }
    }

    // Resize the output vector to keep only the top-p tokens
    candidates->size = last_idx;

    if (ctx) {
        ctx->t_sample_us += ggml_time_us() - t_start_sample_us;
    }
}

void llama_sample_min_p(struct llama_context * ctx, llama_token_data_array * candidates, float p, size_t min_keep) {
    if (p <= 0.0f || !candidates->size) {