Method ingest_images

examples/server/server.cpp:1291–1356

for multiple images processing

    // for multiple images processing
    bool ingest_images(llama_client_slot &slot, int n_batch)
    {
        int image_idx = 0;

        while (image_idx < (int) slot.images.size())
        {
            slot_image &img = slot.images[image_idx];

            // process prefix prompt
            for (int32_t i = 0; i < (int32_t) batch.n_tokens; i += n_batch)
            {
                const int32_t n_tokens = std::min(n_batch, (int32_t) (batch.n_tokens - i));
                llama_batch batch_view = {
                    n_tokens,
                    batch.token    + i,
                    nullptr,
                    batch.pos      + i,
                    batch.n_seq_id + i,
                    batch.seq_id   + i,
                    batch.logits   + i,
                    0, 0, 0, // unused
                };
                if (llama_decode(ctx, batch_view))
                {
                    LOG_TEE("%s : failed to eval\n", __func__);
                    return false;
                }
            }

            // process image with llm
            for (int i = 0; i < img.image_tokens; i += n_batch)
            {
                int n_eval = img.image_tokens - i;
                if (n_eval > n_batch)
                {
                    n_eval = n_batch;
                }

                const int n_embd = llama_n_embd(model);
                llama_batch batch_img = { n_eval, nullptr, (img.image_embedding + i * n_embd), nullptr, nullptr, nullptr, nullptr, slot.n_past, 1, 0, };
                if (llama_decode(ctx, batch_img))
                {
                    LOG_TEE("%s : failed to eval image\n", __func__);
                    return false;
                }
                slot.n_past += n_eval;
            }
            image_idx++;

            llama_batch_clear(batch);

            // append prefix of next image
            const auto json_prompt = (image_idx >= (int) slot.images.size()) ?
                slot.params.input_suffix : // no more images, then process suffix prompt
                (json)(slot.images[image_idx].prefix_prompt);

            std::vector<llama_token> append_tokens = tokenize(json_prompt, false); // has next image
            for (int i = 0; i < (int) append_tokens.size(); ++i)