docs: Website documentation for vllm inferencing using rayserve on AWS Inferentia

website/docs/gen-ai/inference/Neuron/Mistral-7b-inf2.md

@@ -1,6 +1,6 @@
 ---
 title: Mistral-7B on Inferentia2
-sidebar_position: 1
+sidebar_position: 2
 ---
 import CollapsibleContent from '../../../../src/components/CollapsibleContent';
 

website/docs/gen-ai/inference/Neuron/llama2-inf2.md

@@ -1,6 +1,6 @@
 ---
 title: Llama-2 on Inferentia2
-sidebar_position: 3
+sidebar_position: 4
 description: Deploy Llama-2 models on AWS Inferentia accelerators for efficient inference.
 ---
 import CollapsibleContent from '../../../../src/components/CollapsibleContent';

website/docs/gen-ai/inference/Neuron/llama3-inf2.md

@@ -1,6 +1,6 @@
 ---
-title: Llama-3 on Inferentia2
-sidebar_position: 2
+title: Llama-3-8B on Inferentia2
+sidebar_position: 3
 description: Deploy Llama-3 models on AWS Inferentia accelerators for efficient inference.
 ---
 import CollapsibleContent from '../../../../src/components/CollapsibleContent';
@@ -308,4 +308,4 @@ This script will cleanup the environment using `-target` option to ensure all th
 ```bash
 cd ../../../ai-ml/trainium-inferentia/
 ./cleanup.sh
-```
+```

website/docs/gen-ai/inference/Neuron/rayserve-ha.md

@@ -1,6 +1,6 @@
 ---
 title: Ray Serve High Availability
-sidebar_position: 5
+sidebar_position: 6
 ---
 import CollapsibleContent from '../../../../src/components/CollapsibleContent';
 

website/docs/gen-ai/inference/Neuron/stablediffusion-inf2.md

@@ -1,6 +1,6 @@
 ---
 title: Stable Diffusion on Inferentia2
-sidebar_position: 4
+sidebar_position: 5
 ---
 import CollapsibleContent from '../../../../src/components/CollapsibleContent';