Update to include TensorParallelism stuff

Author: seemethere

index.html

@@ -33,7 +33,7 @@ <h3>2024 PyTorch Conference</h3>
       <div class="col-md">
         <h3>PyTorch 2.3</h3>
         <p>
-          PyTorch 2.3 introduces support for user-defined Triton kernels in torch.compile without performance regressions or graph breaks.
+          PyTorch 2.3 introduces support for user-defined Triton kernels in torch.compile as well as improvements for training Large Language Models (LLMS) using native PyTorch. 
         </p>
         <p>
           <a href="/blog/pytorch2-3/">Learn More</a>