From 038b6111631b9bf365ec6e619ca9e4bb272c9403 Mon Sep 17 00:00:00 2001
From: Dan Johansson <dan.johansson@arm.com>
Date: Thu, 26 Sep 2024 14:35:21 +0200
Subject: [PATCH] COMPMID-7502 llama.cpp: README.md updated to increase clarity
 of purpose

This patch attempts to increase clarity of our intent with the llama.cpp
patch located in the llama_cpp subdirectory.
---
 kleidiai-examples/llama_cpp/README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kleidiai-examples/llama_cpp/README.md b/kleidiai-examples/llama_cpp/README.md
index 4fea650..fa379c4 100644
--- a/kleidiai-examples/llama_cpp/README.md
+++ b/kleidiai-examples/llama_cpp/README.md
@@ -47,7 +47,7 @@ These KleidiAI micro-kernels were fundamental to the Cookie and Ada chatbot, whi
 <video autoplay src="https://community.arm.com/cfs-file/__key/telligent-evolution-videotranscoding-securefilestorage/communityserver-blogs-components-weblogfiles-00-00-00-38-23/phi_2D00_3-demo.mp4.mp4" width="640" height="480" controls></video>
 </p>
 
-> ⚠️ This guide is intended as a demonstration of how to integrate the KleidiAI int4 matmul optimized routines in llama.cpp.
+> ⚠️ Please be aware that this guide is only intended as a demonstration of how to integrate the KleidiAI int4 matmul optimized routines in llama.cpp. It is provided without any commitment to support or keep it up to date with current versions of llama.cpp.
 
 ## Target Arm® CPUs