Update README.md

README.md

@@ -38,7 +38,7 @@ Results were also reproduced on Pascal-generation hardware using multi-GPU P104-
 
 Public release v1.0.0.
 
-TurboPrefill is an experimental optimization for llama.cpp that has reached its first public release and is available as open source software.
+TurboPrefill is an experimental open-source optimization for llama.cpp focused on accelerating long-context multi-GPU prefill workloads.
 
 ## GitHub Repository