Method create_memory

subprojects/llama.cpp/src/llama-model.cpp:7478–7622

}

llama_memory_i * llama_model::create_memory(const llama_memory_params & params, const llama_cparams & cparams) const {
    llama_memory_i * res;

    switch (arch) {
        // Models that need specific instantiation should be handled in the
        // switch statement
        case LLM_ARCH_BERT:
        case LLM_ARCH_JINA_BERT_V2:
        case LLM_ARCH_JINA_BERT_V3:
        case LLM_ARCH_NOMIC_BERT:
        case LLM_ARCH_NOMIC_BERT_MOE:
        case LLM_ARCH_NEO_BERT:
        case LLM_ARCH_WAVTOKENIZER_DEC:
        case LLM_ARCH_MODERN_BERT:
        case LLM_ARCH_GEMMA_EMBEDDING:
        case LLM_ARCH_DREAM:
        case LLM_ARCH_LLADA:
        case LLM_ARCH_LLADA_MOE:
        case LLM_ARCH_RND1:
            {
                res = nullptr;
            } break;
        // Models that need standard caching should rely on recurrent/hybrid
        // checks
        default:
            {
                if (llm_arch_is_recurrent(arch)) {
                    res = new llama_memory_recurrent(
                            *this,
                            GGML_TYPE_F32,
                            GGML_TYPE_F32,
                            cparams.offload_kqv,
                            std::max((uint32_t) 1, cparams.n_seq_max),
                            cparams.n_seq_max,
                            nullptr);
                } else if (llm_arch_is_hybrid(arch)) {

                    // The main difference between hybrid architectures is the
                    // layer filters, so pick the right one here
                    llama_memory_hybrid::layer_filter_cb filter_attn = nullptr;
                    llama_memory_hybrid::layer_filter_cb filter_recr = nullptr;
                    if (arch == LLM_ARCH_FALCON_H1) {
                        filter_attn = [&](int32_t) { return true; };
                        filter_recr = [&](int32_t) { return true; };
                    } else if (arch == LLM_ARCH_NEMOTRON_H || arch == LLM_ARCH_NEMOTRON_H_MOE) {
                        filter_attn = [&](int32_t il) {
                            return !hparams.is_recurrent(il) && hparams.n_ff(il) == 0;
                        };
                        filter_recr = [&](int32_t il) {
                            return hparams.is_recurrent(il) && hparams.n_ff(il) == 0;
                        };
                    }

                    if (hparams.swa_type != LLAMA_SWA_TYPE_NONE) {
                        // Use hybrid-iswa for hybrid models with SWA
                        res = new llama_memory_hybrid_iswa(
                            /* model             */ *this,
                            /* attn_type_k       */ params.type_k,