diff --git a/README.md b/README.md
index d01a8fc..add3cbd 100644
--- a/README.md
+++ b/README.md
@@ -25,6 +25,7 @@ pip install -e .
 # or install with dev dependencies if you want to contribute to the project
 pip install -e .[dev] 
 
+pip install grouped_gemm
 pip install flash-attn --no-build-isolation
 ```
 
@@ -87,6 +88,11 @@ Checkout these [inference examples](https://github.com/rhymes-ai/Aria/tree/main/
 
 ## Fine-tuning
 
+> **Note:** For optimal fine-tuning performance, install the optional `grouped_gemm` dependency:
+> ```bash
+> pip install grouped_gemm
+> ```
+
 We offer both LoRA fine-tuning and full parameter tuning, using various dataset types:
 - Single-image datasets
 - Multi-image datasets