Update README.md

Author: iacopPBK

README.md

@@ -1,3 +1,6 @@
+This repo is a wip project, I strongly advise to use official llamacpp.
+
+
 # llama.cpp-gfx906: AMD MI50/MI60/Vega7 fork
 
 This fork is specifically optimized for AMD GFX906 architecture (MI50, MI60, Vega VII) . The aim of this fork is to maximize prompt-processing and inference on a single card. Compatability is now tested on Qwen3 30B-A3B Thinking 2507 (Q4_0) and Qwen3 4B Instruct 2507 (Q4_0).