readme : update hot topics with link to "GPU support" issue

README.md

@@ -9,6 +9,7 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++
 
 **Hot topics:**
 
+- [Add GPU support to ggml](https://github.com/ggerganov/llama.cpp/issues/914)
 - [Roadmap Apr 2023](https://github.com/ggerganov/llama.cpp/discussions/784)
 
 ## Description