add ref to the PR

Author: ngxson

src/llama-kv-cache.cpp

@@ -761,6 +761,7 @@ ggml_tensor * llama_kv_cache_unified::build_rope_shift(
                                 // @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;