Method build_attn_inp_no_cache

subprojects/llama.cpp/src/llama-graph.cpp:1724–1744

}

llm_graph_input_attn_no_cache * llm_graph_context::build_attn_inp_no_cache() const {
    auto inp = std::make_unique<llm_graph_input_attn_no_cache>(hparams, cparams);

    // note: there is no KV cache, so the number of KV values is equal to the number of tokens in the batch
    inp->self_kq_mask = ggml_new_tensor_4d(ctx0, GGML_TYPE_F32, n_tokens, n_tokens, 1, 1);
    ggml_set_input(inp->self_kq_mask);

    inp->self_kq_mask_cnv = cparams.flash_attn ? ggml_cast(ctx0, inp->self_kq_mask, GGML_TYPE_F16) : inp->self_kq_mask;

    if (hparams.swa_type != LLAMA_SWA_TYPE_NONE) {
        inp->self_kq_mask_swa = ggml_new_tensor_4d(ctx0, GGML_TYPE_F32, n_tokens, n_tokens, 1, 1);
        ggml_set_input(inp->self_kq_mask_swa);

        inp->self_kq_mask_swa_cnv = cparams.flash_attn ? ggml_cast(ctx0, inp->self_kq_mask_swa, GGML_TYPE_F16) : inp->self_kq_mask_swa;
    } else {
        inp->self_kq_mask_swa     = nullptr;
        inp->self_kq_mask_swa_cnv = nullptr;
    }

    return (llm_graph_input_attn_no_cache *) res->add_input(std::move(inp));
}

ggml_tensor * llm_graph_context::build_attn(
        llm_graph_input_attn_no_cache * inp,