Method build_rs

subprojects/llama.cpp/src/llama-graph.cpp:2141–2174

}

ggml_tensor * llm_graph_context::build_rs(
        ggml_tensor * s,
        ggml_tensor * state_copy_main,
        ggml_tensor * state_copy_extra,
            int32_t   state_size,
            int32_t   n_seqs,
           uint32_t   n_rs,
           uint32_t   rs_head,
           uint32_t   rs_size,
            int32_t   rs_zero,
        const llm_graph_get_rows_fn & get_state_rows) const {

    ggml_tensor * states = ggml_reshape_2d(ctx0, s, state_size, rs_size);

    // Clear a single state which will then be copied to the other cleared states.
    // Note that this is a no-op when the view is zero-sized.
    ggml_tensor * state_zero = ggml_view_1d(ctx0, states, state_size*(rs_zero >= 0), rs_zero*states->nb[1]*(rs_zero >= 0));
    ggml_build_forward_expand(gf, ggml_scale_inplace(ctx0, state_zero, 0));

    // copy states
    // NOTE: assuming the copy destinations are ALL contained between rs_head and rs_head + n_rs
    // {state_size, rs_size} -> {state_size, n_seqs}
    ggml_tensor * output_states = get_state_rows(ctx0, states, state_copy_main);
    ggml_build_forward_expand(gf, output_states);

    // copy extra states which won't be changed further (between n_seqs and n_rs)
    ggml_tensor * states_extra = ggml_get_rows(ctx0, states, state_copy_extra);
    ggml_build_forward_expand(gf,
        ggml_cpy(ctx0,
            states_extra,
            ggml_view_1d(ctx0, s, state_size*(n_rs - n_seqs), (rs_head + n_seqs)*state_size*ggml_element_size(s))));

    return output_states;
}

static std::unique_ptr<llm_graph_input_rs> build_rs_inp_impl(
           ggml_context * ctx0,