From 596a4aec86b0db7c397ac9c8e407a7ff0a9fdd4f Mon Sep 17 00:00:00 2001
From: Nexesenex <124105151+Nexesenex@users.noreply.github.com>
Date: Thu, 22 Aug 2024 19:12:25 +0200
Subject: [PATCH] Readd variable attn_k, attn_q, attn_o after merge

---
 src/llama.cpp | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/src/llama.cpp b/src/llama.cpp
index 6191741ff..a91ed5c60 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -17328,6 +17328,9 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
             n_attn_layer *= 3;
         }
         GGML_ASSERT((qs.n_attention_wv == n_attn_layer) && "n_attention_wv is unexpected");
+        GGML_ASSERT((qs.n_attention_wk == n_attn_layer) && "n_attention_wk is unexpected");
+        GGML_ASSERT((qs.n_attention_wq == n_attn_layer) && "n_attention_wq is unexpected");
+        GGML_ASSERT((qs.n_attention_wo == n_attn_layer) && "n_attention_wo is unexpected");
     }
 
     size_t total_size_org = 0;