update CUDA -v

README.md

@@ -297,7 +297,7 @@ Client 2         Size of data: 1630      Labels:  [0 3 6 9]
     - HARCNN() in [Convolutional neural networks for human activity recognition using mobile sensors](https://eudl.eu/pdf/10.4108/icst.mobicase.2014.257786)
 
 ## Environments
-Install [CUDA v11.6](https://developer.nvidia.com/cuda-11-6-0-download-archive). 
+Install [CUDA](https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html). 
 
 Install [conda latest](https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh) and activate conda. 
 

docs/quickstart.html

@@ -179,7 +179,7 @@ <h2>Installation</h2>
                 <ol>
                     <li><p>You can install PFLlib via <a href="https://git-scm.com/">git</a>:</p></li>
                     <pre>git clone https://github.com/TsingZ0/PFLlib.git</pre>
-                    <li><p>Then install <a href="https://developer.nvidia.com/cuda-11-6-0-download-archive">CUDA v11.6</a> following NVIDIA's instructions.</p></li>
+                    <li><p>Then install <a href="https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html">CUDA</a> following NVIDIA's instructions.</p></li>
                     <li><p>Install the latest version of <a href="https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh">conda</a> and activate conda.</p></li>
                     <li><p>Install the required Python dependencies using <code>env_cuda_latest.yaml</code> and conda:</p></li>
                     <pre>conda env create -f env_cuda_latest.yaml # You may need to downgrade the torch using pip to match the CUDA version.</pre>