Deploying to gh-pages from @ dstackai/dstack@a05cf74 🚀

Author: peterschmidt85

assets/images/social/examples.png

@@ -3994,6 +3994,7 @@ <h2 id="limitations-and-roadmap">Limitations and roadmap<a class="headerlink" hr
 <ul>
 <li>Enabling prefill and decode worker separation for full disaggregation (today, only standard workers are supported).</li>
 <li>Introducing auto-scaling based on TTFT (Time to First Token) and ITL (Inter-Token Latency), complementing the current requests-per-second scaling metric.</li>
+<li>Supporting multi-node replicas, enabling a single replica to span multiple nodes instead of being limited to one.</li>
 <li>Extending native support to more emerging inference stacks.</li>
 </ul>
 <h2 id="whats-next">What's next?<a class="headerlink" href="#whats-next" title="Permanent link">&para;</a></h2>