[Docs] Extracted Distributed training examples into a separate section; plus minor refactoring (#2614)

Author: peterschmidt85

docs/assets/stylesheets/extra.css

@@ -546,7 +546,7 @@ h4.doc-heading {
         background-color: transparent;
         border-radius: 3px;
         border: 0.5px solid rgba(0, 0, 0, 0.87);
-        height: 1.95rem;
+        /* height: 1.95rem; */
     }
 
     [data-md-color-primary=white] .md-search__form:hover {
@@ -813,13 +813,13 @@ body {
         z-index: 101;
     }
 
-    .md-search__form::before {
+    /* .md-search__form::before {
         content: "⌘";
         color: white;
         font-weight: 600;
         position: absolute;
         padding: 7px;
-        margin: 4.5px;
+        margin: 3.5px;
         font-size: .65rem;
         background-color: rgba(0,0,0,.87);
         border-radius: 5px;
@@ -835,7 +835,7 @@ body {
         font-weight: 600;
         position: absolute;
         padding: 7px;
-        margin: 4.5px;
+        margin: 3.5px;
         font-size: .65rem;
         background-color: rgba(0,0,0,.87);
         border-radius: 5px;
@@ -844,7 +844,7 @@ body {
         /*z-index: 1;*/
         width: 30px;
         text-align: center;
-    }
+    } */
 
     .md-nav--lifted > .md-nav__list > .md-nav__item > [for] {
         display: none;

docs/blog/posts/mpi.md

@@ -31,7 +31,7 @@ cluster usage—we’ve added support for it.
 
 Below is an example of a task that runs AllReduce test on 2 nodes, each with 4 GPUs (8 processes in total).
 
-<div editor-title="examples/misc/nccl-tests/.dstack.yml">
+<div editor-title="examples/distributed-training/nccl-tests/.dstack.yml">
 
 ```yaml
 type: task
@@ -101,5 +101,5 @@ as well as use MPI for other tasks.
 
 !!! info "What's next?"
     1. Learn more about [dev environments](../../docs/concepts/dev-environments.md), [tasks](../../docs/concepts/tasks.md), [services](../../docs/concepts/services.md), and [fleets](../../docs/concepts/fleets.md)
-    2. Check the [NCCL tests](../../examples/misc/nccl-tests/index.md) example
+    2. Check the [NCCL tests](../../examples/distributed-training/nccl-tests/index.md) example
     2. Join [Discord :material-arrow-top-right-thin:{ .external }](https://discord.gg/u8SmfwPpMd){:target="_blank"}

docs/docs/guides/protips.md

@@ -30,9 +30,8 @@ To change the default idle duration, set
 [`idle_duration`](../reference/dstack.yml/fleet.md#idle_duration) in the run configuration (e.g., `0s`, `1m`, or `off` for
 unlimited).
 
-!!! info "Fleets"
-    For greater control over fleet provisioning, configuration, and lifecycle management, it is recommended to use
-    [fleets](../concepts/fleets.md) directly.
+> For greater control over fleet provisioning, configuration, and lifecycle management, it is recommended to use
+> [fleets](../concepts/fleets.md) directly.
 
 ## Volumes
 

docs/docs/quickstart.md

@@ -207,5 +207,5 @@ Something not working? See the [troubleshooting](guides/troubleshooting.md) guid
 
 !!! info "What's next?"
     1. Read about [backends](concepts/backends.md),  [dev environments](concepts/dev-environments.md), [tasks](concepts/tasks.md), and [services](concepts/services.md)
-    2. Join [Discord :material-arrow-top-right-thin:{ .external }](https://discord.gg/u8SmfwPpMd)
-    3. Browse [examples](https://dstack.ai/examples)
+    2. Browse [examples](../examples.md)
+    3. Join [Discord :material-arrow-top-right-thin:{ .external }](https://discord.gg/u8SmfwPpMd)

docs/examples.md

@@ -12,7 +12,79 @@ hide:
 }
 </style>
 
+## Fine-tuning
+
+<div class="tx-landing__highlights_grid">
+    <a href="/examples/fine-tuning/axolotl"
+       class="feature-cell">
+        <h3>
+            Axolotl
+        </h3>
+
+        <p>
+            Fine-tune Llama 4 on a custom dataset using Axolotl.
+        </p>
+    </a>
+
+    <a href="/examples/fine-tuning/trl"
+       class="feature-cell">
+        <h3>
+            TRL
+        </h3>
+
+        <p>
+            Fine-tune Llama 3.1 8B on a custom dataset using TRL.
+        </p>
+    </a>
+</div>
+
+## Distributed training
+
+<div class="tx-landing__highlights_grid">
+    <a href="/examples/distributed-training/nccl-tests"
+       class="feature-cell sky">
+        <h3>
+            NCCL tests
+        </h3>
+
+        <p>
+            Run multi-node NCCL tests with MPI
+        </p>
+    </a>
+    <a href="/examples/distributed-training/rccl-tests"
+       class="feature-cell sky">
+        <h3>
+            RCCL tests
+        </h3>
+
+        <p>
+            Run multi-node RCCL tests with MPI
+        </p>
+    </a>
+    <a href="/examples/distributed-training/a3mega-clusters"
+       class="feature-cell sky">
+        <h3>
+            A3 Mega
+        </h3>
+
+        <p>
+            Set up GCP A3 Mega clusters with optimized networking
+        </p>
+    </a>
+    <a href="/examples/distributed-training/a3high-clusters"
+       class="feature-cell sky">
+        <h3>
+            A3 High
+        </h3>
+
+        <p>
+            Set up GCP A3 High clusters with optimized networking
+        </p>
+    </a>
+</div>
+
 ## Deployment
+
 <div class="tx-landing__highlights_grid">
     <a href="/examples/deployment/sglang" 
        class="feature-cell">
@@ -61,32 +133,6 @@ hide:
     </a>
 </div>
 
-## Fine-tuning
-
-<div class="tx-landing__highlights_grid">
-    <a href="/examples/fine-tuning/axolotl"
-       class="feature-cell">
-        <h3>
-            Axolotl
-        </h3>
-
-        <p>
-            Fine-tune Llama 4 on a custom dataset using Axolotl.
-        </p>
-    </a>
-
-    <a href="/examples/fine-tuning/trl"
-       class="feature-cell">
-        <h3>
-            TRL
-        </h3>
-
-        <p>
-            Fine-tune Llama 3.1 8B on a custom dataset using TRL.
-        </p>
-    </a>
-</div>
-
 ## Accelerators
 
 <div class="tx-landing__highlights_grid">
@@ -173,44 +219,4 @@ hide:
             Use Docker and Docker Compose inside runs
         </p>
     </a>
-    <a href="/examples/misc/nccl-tests"
-       class="feature-cell sky">
-        <h3>
-            NCCL tests
-        </h3>
-
-        <p>
-            Run multi-node NCCL tests with MPI
-        </p>
-    </a>
-    <a href="/examples/misc/rccl-tests"
-       class="feature-cell sky">
-        <h3>
-            RCCL tests
-        </h3>
-
-        <p>
-            Run multi-node RCCL tests with MPI
-        </p>
-    </a>
-    <a href="/examples/misc/a3mega-clusters"
-       class="feature-cell sky">
-        <h3>
-            A3 Mega
-        </h3>
-
-        <p>
-            Set up GCP A3 Mega clusters with optimized networking
-        </p>
-    </a>
-    <a href="/examples/misc/a3high-clusters"
-       class="feature-cell sky">
-        <h3>
-            A3 High
-        </h3>
-
-        <p>
-            Set up GCP A3 High clusters with optimized networking
-        </p>
-    </a>
 </div>

…s/examples/misc/a3high-clusters/index.md …ibuted-training/a3high-clusters/index.mddocs/examples/misc/a3high-clusters/index.md renamed to docs/examples/distributed-training/a3high-clusters/index.md docs/examples/misc/a3high-clusters/index.md renamed to docs/examples/distributed-training/a3high-clusters/index.md

@@ -61,8 +61,8 @@
     {% endif %}-->
 
     <div class="md-header__buttons">
-      <a href="https://github.com/dstackai/dstack" target="_blank" class="md-button md-button--primary github">GitHub</a>
-      <!--<a href="https://discord.gg/u8SmfwPpMd" target="_blank" class="md-button md-button-secondary discord">Discord</a>-->
+      <a href="https://github.com/dstackai/dstack" target="_blank" class="md-button md-button-secondary github external">GitHub</a>
+      <a href="https://discord.gg/u8SmfwPpMd" target="_blank" class="md-button md-button-secondary discord external">Discord</a>
     </div>
   </nav>
   {% if "navigation.tabs.sticky" in features %}