Deployed 998776c to 0.3 with MkDocs 1.6.0 and mike 2.1.3

Author: gitlawr

0.3/overview/index.html

@@ -1005,7 +1005,7 @@ <h3 id="key-features">Key Features</h3>
 <li><strong>Supports a Wide Variety of Hardware:</strong> Run with different brands of GPUs in Apple MacBooks, Windows PCs, and Linux servers.</li>
 <li><strong>Scales with Your GPU Inventory:</strong> Easily add more GPUs or nodes to scale up your operations.</li>
 <li><strong>Distributed Inference</strong>: Supports both single-node multi-GPU and multi-node inference and serving.</li>
-<li><strong>Multiple Inference Backends</strong>: Supports llama-box(llama.cpp) and vLLM as the inference backend.</li>
+<li><strong>Multiple Inference Backends</strong>: Supports llama-box (llama.cpp) and vLLM as the inference backend.</li>
 <li><strong>Lightweight Python Package:</strong> Minimal dependencies and operational overhead.</li>
 <li><strong>OpenAI-compatible APIs:</strong> Serve APIs that are compatible with OpenAI standards.</li>
 <li><strong>User and API key management:</strong> Simplified management of users and API keys.</li>

0.3/search/search_index.json

@@ -1429,11 +1429,11 @@ <h4 id="manual">Manual</h4>
 </ul>
 <p>Select a GPU from the list. The model instance will attempt to deploy to this GPU if resources permit.</p>
 <h3 id="backend">Backend</h3>
-<p>The inference backend. Currently, GPUStack supports two backends: llama-box and vLLM. GPUStack automatically selects the backend based on the model's information.</p>
+<p>The inference backend. Currently, GPUStack supports two backends: llama-box and vLLM. GPUStack automatically selects the backend based on the model's configuration.</p>
 <p>For more details, please refer to the <a href="../inference-backends/">Inference Backends</a> section.</p>
 <h3 id="backend-parameters">Backend Parameters</h3>
-<p>Input the parameters for the backend you want to customize while running the model instance. Should be in the format <code>--parameter=value</code>, <code>--bool-parameter</code> or separate <code>--parameter</code> and <code>value</code> in two fields.
-For example, <code>--ctx-size=8192</code> for llama-box.</p>
+<p>Input the parameters for the backend you want to customize when running the model. The parameter should be in the format <code>--parameter=value</code>, <code>--bool-parameter</code> or as separate fields for <code>--parameter</code> and <code>value</code>.
+For example, use <code>--ctx-size=8192</code> for llama-box.</p>
 <p>For full list of supported parameters, please refer to the <a href="../inference-backends/">Inference Backends</a> section.</p>
 <h3 id="allow-cpu-offloading">Allow CPU Offloading</h3>
 <div class="admonition note">