Feature/sg 000 add note that qat only supports gpu

documentation/source/ptq_qat.md

@@ -22,6 +22,8 @@ In this tutorial, we’ll compare post-training quantization (PTQ) to quantizati
 
 For mode detailed information and theoretical background, refer to this [NVIDIA whitepaper](https://arxiv.org/pdf/2004.09602.pdf) and [this practical guide from PyTorch](https://pytorch.org/blog/quantization-in-practice/).
 
+**Note: quantization is currently supported exclusively for GPU and TensorRT environments.**
+
 
 ## Quantization: FP32 vs FP16 vs INT8
 Quantization is a model size reduction technique that converts model weights from high-precision floating-point representation (32-bit float) to low-precision floating-point (FP) representation, such as 16-bit or 8-bit.

documentation/source/qat_ptq_yolo_nas.md

@@ -15,6 +15,7 @@ Pre-requisites:
 - [Training with configuration files](https://github.com/Deci-AI/super-gradients/blob/master/documentation/source/configuration_files.md)
 - [PTQ and QAT](https://github.com/Deci-AI/super-gradients/blob/master/documentation/source/ptq_qat.md)
 
+**Note: quantization is currently supported exclusively for GPU and TensorRT environments.**
 
 Now, let's get to it.
 

notebooks/PTQ_and_QAT_for_classification.ipynb

@@ -32,7 +32,9 @@
     "\n",
     "Full tutorial can be found [here](https://github.com/Deci-AI/super-gradients/blob/master/documentation/source/ptq_qat.md)\n",
     "\n",
-    "SuperGradient's Recipes for PTQ/QAT can be found [here](https://github.com/Deci-AI/super-gradients/tree/master/src/super_gradients/recipes/quantization_params)\n"
+    "SuperGradient's Recipes for PTQ/QAT can be found [here](https://github.com/Deci-AI/super-gradients/tree/master/src/super_gradients/recipes/quantization_params)\n",
+    "\n",
+    "**Note: quantization is currently supported exclusively for GPU and TensorRT environments.**"
    ]
   },
   {
@@ -1854,4 +1856,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 0
-}
+}