Method build_rope_shift

subprojects/llama.cpp/src/llama-kv-cache.cpp:1533–1576

}

ggml_tensor * llama_kv_cache::build_rope_shift(
        const llama_cparams & cparams,
               ggml_context * ctx,
                ggml_tensor * cur,
                ggml_tensor * shift,
                ggml_tensor * factors,
                      float   freq_base,
                      float   freq_scale) const {
    const auto & n_ctx_orig = cparams.n_ctx_orig_yarn;

    const auto & yarn_ext_factor  = cparams.yarn_ext_factor;
    const auto & yarn_beta_fast   = cparams.yarn_beta_fast;
    const auto & yarn_beta_slow   = cparams.yarn_beta_slow;
    const auto & yarn_attn_factor = cparams.yarn_attn_factor;

    const auto & n_rot     = hparams.n_rot;
    const auto & rope_type = hparams.rope_type == LLAMA_ROPE_TYPE_MROPE || hparams.rope_type == LLAMA_ROPE_TYPE_IMROPE
                                // @ngxson : this is a workaround
                                // for M-RoPE, we want to rotate the whole vector when doing KV shift
                                // a normal RoPE should work, we just need to use the correct ordering
                                // ref: https://github.com/ggml-org/llama.cpp/pull/13870
                                ? LLAMA_ROPE_TYPE_NEOX
                                : hparams.rope_type;

    ggml_tensor * tmp;

    if (ggml_is_quantized(cur->type)) {
        // dequantize to f32 -> RoPE -> quantize back
        tmp = ggml_cast(ctx, cur, GGML_TYPE_F32);

        tmp = ggml_rope_ext(ctx, tmp,
                shift, factors, n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
                yarn_ext_factor, yarn_attn_factor, yarn_beta_fast, yarn_beta_slow);

        tmp = ggml_cpy(ctx, tmp, cur);
    } else {
        // we rotate only the first n_rot dimensions
        tmp = ggml_rope_ext_inplace(ctx, cur,
                shift, factors, n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
                yarn_ext_factor, yarn_attn_factor, yarn_beta_fast, yarn_beta_slow);
    }

    return tmp;
}

class llm_graph_input_k_shift : public llm_graph_input_i {
public: