Method decode

tests/test-backend-sampler.cpp:116–180

    }

    bool decode(const std::map<llama_seq_id, std::string> & prompts) {
        GGML_ASSERT(ctx);

        last_batch_info.clear();
        llama_batch batch = llama_batch_init(512, 0, prompts.size());

        for (const auto & [seq_id, prompt] : prompts) {
            std::vector<llama_token> tokens;
            tokens.push_back(llama_vocab_bos(vocab));

            std::vector<llama_token> prompt_tokens(32);
            int n_tokens = llama_tokenize(vocab, prompt.c_str(), prompt.length(),
                                           prompt_tokens.data(), prompt_tokens.size(),
                                           false, false);
            if (n_tokens < 0) {
                fprintf(stderr, "Warning: tokenization failed for seq_id %d\n", seq_id);
                llama_batch_free(batch);
                return false;
            }

            for (int i = 0; i < n_tokens; i++) {
                tokens.push_back(prompt_tokens[i]);
            }

            if (seq_positions.find(seq_id) == seq_positions.end()) {
                seq_positions[seq_id] = 0;
            }

            int32_t start_pos = seq_positions[seq_id];
            for (size_t i = 0; i < tokens.size(); i++) {
                common_batch_add(batch, tokens[i], start_pos + i, { seq_id }, i == tokens.size() - 1);
            }

            seq_positions[seq_id] = start_pos + tokens.size();
        }


        printf("Batch contents:\n");
        printf("n_tokens: %d\n", batch.n_tokens);
        for (int i = 0; i < batch.n_tokens; i++) {
            printf("token[%d]: tok=%-5d, pos=%d, n_seq_id=%d, seq_ids=[", i, batch.token[i], batch.pos[i], batch.n_seq_id[i]);

            for (int j = 0; j < batch.n_seq_id[i]; j++) {
                printf("%d%s", batch.seq_id[i][j], j < batch.n_seq_id[i]-1 ? ", " : "");
            }
            printf("], logits=%d\n", batch.logits[i]);
        }

        if (llama_decode(ctx.get(), batch) != 0) {
            fprintf(stderr, "Warning: llama_decode failed\n");
            llama_batch_free(batch);
            return false;
        }

        // Build mapping from seq id to batch token idx
        for (int i = 0; i < batch.n_tokens; i++) {
            if (batch.logits[i]) {
                llama_seq_id seq_id = batch.seq_id[i][0];