Update README.md

Author: Gadflyii

README.md

@@ -1,3 +1,10 @@
+This fork enables Intel AMX acceleration for 4th, 5th, and 6th generation Xeon / Xeon-w processors in CPU / GPU hybrids. 
+
+Build with all the normal AMX flags (unchanged from upstream), and use "--amx" in you run commands.
+
+You can use --AMX on all excutables, tested with CLI / Server / and Bench.
+
+
 # llama.cpp
 
 ![llama](https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png)