Update README.md

README.md

@@ -414,10 +414,6 @@ body {
             <h3>GGUF</h3>
             <p>CPU-focused inference</p>
         </a>
-        <a href="https://github.com/turboderp-org/exllamav2" class="link-card" target="_blank">
-            <h3>EXL2</h3>
-            <p>High-speed GPU inference (Ampere Optimized)</p>
-        </a>
         <a href="https://github.com/turboderp-org/exllamav3" class="link-card" target="_blank">
             <h3>EXL3</h3>
             <p>Next-gen GPU optimization</p>