readme : add deprecation notice

Author: ggerganov

README.md

@@ -10,7 +10,8 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++
 
 ### Hot topics
 
-- ⚠️ Incoming backends: https://github.com/ggerganov/llama.cpp/discussions/5138
+- Deprecated LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD: https://github.com/ggerganov/llama.cpp/discussions/5240
+- Incoming backends: https://github.com/ggerganov/llama.cpp/discussions/5138
   - [SYCL backend](README-sycl.md) is ready (1/28/2024), support Linux/Windows in Intel GPUs (iGPU, Arc/Flex/Max series)
 - New SOTA quantized models, including pure 2-bits: https://huggingface.co/ikawrakow
 - Collecting Apple Silicon performance stats: