Method init_batch

subprojects/llama.cpp/src/llama-memory-hybrid.cpp:62–112

    )) {}

llama_memory_context_ptr llama_memory_hybrid::init_batch(llama_batch_allocr & balloc, uint32_t n_ubatch, bool embd_all) {
    do {
        balloc.split_reset();

        // follow the recurrent pattern for creating the ubatch splits
        std::vector<llama_ubatch> ubatches;

        while (true) {
            llama_ubatch ubatch;

            if (embd_all) {
                // if all tokens are output, split by sequence
                ubatch = balloc.split_seq(n_ubatch);
            } else {
                // TODO: non-sequential equal split can be done if using unified KV cache
                //       for simplicity, we always use sequential equal split for now
                ubatch = balloc.split_equal(n_ubatch, true);
            }

            if (ubatch.n_tokens == 0) {
                break;
            }

            ubatches.push_back(std::move(ubatch)); // NOLINT
        }

        if (balloc.get_n_used() < balloc.get_n_tokens()) {
            // failed to find a suitable split
            break;
        }

        // prepare the recurrent batches first
        if (!mem_recr->prepare(ubatches)) {
            // TODO: will the recurrent cache be in an undefined context at this point?
            LLAMA_LOG_ERROR("%s: failed to prepare recurrent ubatches\n", __func__);
            return std::make_unique<llama_memory_hybrid_context>(LLAMA_MEMORY_STATUS_FAILED_PREPARE);
        }

        // prepare the attention cache
        auto heads_attn = mem_attn->prepare(ubatches);
        if (heads_attn.empty()) {
            LLAMA_LOG_ERROR("%s: failed to prepare attention ubatches\n", __func__);
            return std::make_unique<llama_memory_hybrid_context>(LLAMA_MEMORY_STATUS_FAILED_PREPARE);
        }

        return std::make_unique<llama_memory_hybrid_context>(
                this, std::move(heads_attn), std::move(ubatches));
    } while(false);

    return std::make_unique<llama_memory_hybrid_context>(LLAMA_MEMORY_STATUS_FAILED_PREPARE);
}

llama_memory_context_ptr llama_memory_hybrid::init_full() {
    return std::make_unique<llama_memory_hybrid_context>(this);