Function build_rs_inp_impl

subprojects/llama.cpp/src/llama-graph.cpp:2176–2196

}

static std::unique_ptr<llm_graph_input_rs> build_rs_inp_impl(
           ggml_context * ctx0,
     const llama_ubatch & ubatch,
    const llama_memory_recurrent_context * mctx_cur) {

    auto inp = std::make_unique<llm_graph_input_rs>(mctx_cur);

    const int64_t n_rs   = mctx_cur->get_n_rs();
    const int64_t n_seqs = ubatch.n_seqs;

    inp->s_copy = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_rs);
    ggml_set_input(inp->s_copy);

    inp->s_copy_main  = ggml_view_1d(ctx0, inp->s_copy, n_seqs, 0);
    inp->s_copy_extra = ggml_view_1d(ctx0, inp->s_copy, n_rs - n_seqs, n_seqs * inp->s_copy->nb[0]);

    inp->head = mctx_cur->get_head();
    inp->rs_z = mctx_cur->get_rs_z();

    return inp;
}

llm_graph_input_rs * llm_graph_context::build_rs_inp() const {
    const auto * mctx_cur = static_cast<const llama_memory_recurrent_context *>(mctx);