Built site for gh-pages

docs/lora_optims.html

@@ -491,6 +491,7 @@ memory usage during the forward and backward passes of these calculations.</p>
 <li><code>qwen2</code></li>
 <li><code>gemma</code></li>
 <li><code>gemma2</code></li>
+<li><code>gemma3</code></li>
 </ul>
 <details>
 <p>The set of models we support is currently limited by our attention patching strategy,