Skip to content

Commit 71a1749

Browse files
deploy: 1911e62
1 parent 43ec2c8 commit 71a1749

File tree

77 files changed

+75
-75
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

77 files changed

+75
-75
lines changed

404.html

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
<meta name="generator" content="Docusaurus v3.9.0">
66
<title data-rh="true">Page Not Found | AI on EKS</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://awslabs.github.io/ai-on-eks/404.html"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docusaurus_tag" content="default"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docsearch:docusaurus_tag" content="default"><meta data-rh="true" property="og:title" content="Page Not Found | AI on EKS"><link data-rh="true" rel="icon" href="/ai-on-eks/img/header-icon.png"><link data-rh="true" rel="canonical" href="https://awslabs.github.io/ai-on-eks/404.html"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/404.html" hreflang="en"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/404.html" hreflang="x-default"><link rel="stylesheet" href="/ai-on-eks/assets/css/styles.c270b852.css">
77
<script src="/ai-on-eks/assets/js/runtime~main.89d82209.js" defer="defer"></script>
8-
<script src="/ai-on-eks/assets/js/main.981a63f3.js" defer="defer"></script>
8+
<script src="/ai-on-eks/assets/js/main.278e6a60.js" defer="defer"></script>
99
</head>
1010
<body class="navigation-with-keyboard">
1111
<svg style="display: none;"><defs>
Lines changed: 2 additions & 2 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

docs/blueprints.html

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
<meta name="generator" content="Docusaurus v3.9.0">
66
<title data-rh="true">AI on EKS</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://awslabs.github.io/ai-on-eks/docs/blueprints"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="current"><meta data-rh="true" name="docusaurus_tag" content="docs-default-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-current"><meta data-rh="true" property="og:title" content="AI on EKS"><meta data-rh="true" name="description" content="Welcome to AI on Amazon Elastic Kubernetes Service (EKS), your gateway to harnessing the power of Large Language Models (LLMs) for a wide range of applications. This introduction page serves as your starting point to explore our architectural patterns and blueprints for Training, Fine-tuning, and Inference using the latest LLMs."><meta data-rh="true" property="og:description" content="Welcome to AI on Amazon Elastic Kubernetes Service (EKS), your gateway to harnessing the power of Large Language Models (LLMs) for a wide range of applications. This introduction page serves as your starting point to explore our architectural patterns and blueprints for Training, Fine-tuning, and Inference using the latest LLMs."><link data-rh="true" rel="icon" href="/ai-on-eks/img/header-icon.png"><link data-rh="true" rel="canonical" href="https://awslabs.github.io/ai-on-eks/docs/blueprints"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints" hreflang="en"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Overview","item":"https://awslabs.github.io/ai-on-eks/docs/blueprints/"}]}</script><link rel="stylesheet" href="/ai-on-eks/assets/css/styles.c270b852.css">
77
<script src="/ai-on-eks/assets/js/runtime~main.89d82209.js" defer="defer"></script>
8-
<script src="/ai-on-eks/assets/js/main.981a63f3.js" defer="defer"></script>
8+
<script src="/ai-on-eks/assets/js/main.278e6a60.js" defer="defer"></script>
99
</head>
1010
<body class="navigation-with-keyboard">
1111
<svg style="display: none;"><defs>

docs/blueprints/gateways/envoy-gateway.html

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
<meta name="generator" content="Docusaurus v3.9.0">
66
<title data-rh="true">Envoy gateway | AI on EKS</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://awslabs.github.io/ai-on-eks/docs/blueprints/gateways/envoy-gateway"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="current"><meta data-rh="true" name="docusaurus_tag" content="docs-default-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-current"><meta data-rh="true" property="og:title" content="Envoy gateway | AI on EKS"><meta data-rh="true" name="description" content="Organizations deploying AI applications face a fundamental challenge: no single model serves all needs. Developers may choose Claude for long-context analysis, OpenAI for reasoning tasks, and DeepSeek for cost-sensitive workloads. The problem is that each model provider uses different APIs. Without centralized control, teams can&#x27;t easily switch providers, get visibility into utilization, or enforce quotas."><meta data-rh="true" property="og:description" content="Organizations deploying AI applications face a fundamental challenge: no single model serves all needs. Developers may choose Claude for long-context analysis, OpenAI for reasoning tasks, and DeepSeek for cost-sensitive workloads. The problem is that each model provider uses different APIs. Without centralized control, teams can&#x27;t easily switch providers, get visibility into utilization, or enforce quotas."><link data-rh="true" rel="icon" href="/ai-on-eks/img/header-icon.png"><link data-rh="true" rel="canonical" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/gateways/envoy-gateway"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/gateways/envoy-gateway" hreflang="en"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/gateways/envoy-gateway" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Envoy Gateway implementation on EKS","item":"https://awslabs.github.io/ai-on-eks/docs/blueprints/gateways/envoy-gateway"}]}</script><link rel="stylesheet" href="/ai-on-eks/assets/css/styles.c270b852.css">
77
<script src="/ai-on-eks/assets/js/runtime~main.89d82209.js" defer="defer"></script>
8-
<script src="/ai-on-eks/assets/js/main.981a63f3.js" defer="defer"></script>
8+
<script src="/ai-on-eks/assets/js/main.278e6a60.js" defer="defer"></script>
99
</head>
1010
<body class="navigation-with-keyboard">
1111
<svg style="display: none;"><defs>

docs/blueprints/inference.html

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
<meta name="generator" content="Docusaurus v3.9.0">
66
<title data-rh="true">Inference on EKS | AI on EKS</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="current"><meta data-rh="true" name="docusaurus_tag" content="docs-default-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-current"><meta data-rh="true" property="og:title" content="Inference on EKS | AI on EKS"><meta data-rh="true" name="description" content="AI on EKS provides comprehensive solutions for deploying AI/ML inference workloads on Amazon EKS, supporting both GPU and AWS Neuron (Inferentia/Trainium) hardware configurations."><meta data-rh="true" property="og:description" content="AI on EKS provides comprehensive solutions for deploying AI/ML inference workloads on Amazon EKS, supporting both GPU and AWS Neuron (Inferentia/Trainium) hardware configurations."><link data-rh="true" rel="icon" href="/ai-on-eks/img/header-icon.png"><link data-rh="true" rel="canonical" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference" hreflang="en"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Inference on EKS","item":"https://awslabs.github.io/ai-on-eks/docs/category/inference-on-eks"},{"@type":"ListItem","position":2,"name":"Overview","item":"https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/"}]}</script><link rel="stylesheet" href="/ai-on-eks/assets/css/styles.c270b852.css">
77
<script src="/ai-on-eks/assets/js/runtime~main.89d82209.js" defer="defer"></script>
8-
<script src="/ai-on-eks/assets/js/main.981a63f3.js" defer="defer"></script>
8+
<script src="/ai-on-eks/assets/js/main.278e6a60.js" defer="defer"></script>
99
</head>
1010
<body class="navigation-with-keyboard">
1111
<svg style="display: none;"><defs>

docs/blueprints/inference/GPUs/aibrix-deepseek-distill.html

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
<meta name="generator" content="Docusaurus v3.9.0">
66
<title data-rh="true">AIBrix | AI on EKS</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/aibrix-deepseek-distill"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="current"><meta data-rh="true" name="docusaurus_tag" content="docs-default-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-current"><meta data-rh="true" property="og:title" content="AIBrix | AI on EKS"><meta data-rh="true" name="description" content="AIBrix is an open source initiative designed to provide essential building blocks to construct scalable GenAI inference infrastructure. AIBrix delivers a cloud-native solution optimized for deploying, managing, and scaling large language model (LLM) inference, tailored specifically to enterprise needs."><meta data-rh="true" property="og:description" content="AIBrix is an open source initiative designed to provide essential building blocks to construct scalable GenAI inference infrastructure. AIBrix delivers a cloud-native solution optimized for deploying, managing, and scaling large language model (LLM) inference, tailored specifically to enterprise needs."><link data-rh="true" rel="icon" href="/ai-on-eks/img/header-icon.png"><link data-rh="true" rel="canonical" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/aibrix-deepseek-distill"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/aibrix-deepseek-distill" hreflang="en"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/aibrix-deepseek-distill" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Inference on EKS","item":"https://awslabs.github.io/ai-on-eks/docs/category/inference-on-eks"},{"@type":"ListItem","position":2,"name":"GPU Inference on EKS","item":"https://awslabs.github.io/ai-on-eks/docs/category/gpu-inference-on-eks"},{"@type":"ListItem","position":3,"name":"AIBrix on EKS","item":"https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/aibrix-deepseek-distill"}]}</script><link rel="stylesheet" href="/ai-on-eks/assets/css/styles.c270b852.css">
77
<script src="/ai-on-eks/assets/js/runtime~main.89d82209.js" defer="defer"></script>
8-
<script src="/ai-on-eks/assets/js/main.981a63f3.js" defer="defer"></script>
8+
<script src="/ai-on-eks/assets/js/main.278e6a60.js" defer="defer"></script>
99
</head>
1010
<body class="navigation-with-keyboard">
1111
<svg style="display: none;"><defs>

docs/blueprints/inference/GPUs/llama4-vllm.html

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
<meta name="generator" content="Docusaurus v3.9.0">
66
<title data-rh="true">Llama 4 with vLLM on EKS | AI on EKS</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/llama4-vllm"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="current"><meta data-rh="true" name="docusaurus_tag" content="docs-default-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-current"><meta data-rh="true" property="og:title" content="Llama 4 with vLLM on EKS | AI on EKS"><meta data-rh="true" name="description" content="In this guide, we&#x27;ll explore deploying Llama 4 models using vLLM inference engine on Amazon EKS with EKS Auto Mode for automatic GPU node provisioning."><meta data-rh="true" property="og:description" content="In this guide, we&#x27;ll explore deploying Llama 4 models using vLLM inference engine on Amazon EKS with EKS Auto Mode for automatic GPU node provisioning."><link data-rh="true" rel="icon" href="/ai-on-eks/img/header-icon.png"><link data-rh="true" rel="canonical" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/llama4-vllm"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/llama4-vllm" hreflang="en"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/llama4-vllm" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Inference on EKS","item":"https://awslabs.github.io/ai-on-eks/docs/category/inference-on-eks"},{"@type":"ListItem","position":2,"name":"GPU Inference on EKS","item":"https://awslabs.github.io/ai-on-eks/docs/category/gpu-inference-on-eks"},{"@type":"ListItem","position":3,"name":"Llama 4 with vLLM on EKS","item":"https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/llama4-vllm"}]}</script><link rel="stylesheet" href="/ai-on-eks/assets/css/styles.c270b852.css">
77
<script src="/ai-on-eks/assets/js/runtime~main.89d82209.js" defer="defer"></script>
8-
<script src="/ai-on-eks/assets/js/main.981a63f3.js" defer="defer"></script>
8+
<script src="/ai-on-eks/assets/js/main.278e6a60.js" defer="defer"></script>
99
</head>
1010
<body class="navigation-with-keyboard">
1111
<svg style="display: none;"><defs>

docs/blueprints/inference/GPUs/nvidia-deep-research.html

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
<meta name="generator" content="Docusaurus v3.9.0">
66
<title data-rh="true">NVIDIA Enterprise RAG and AI-Q Research Assistant on EKS | AI on EKS</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/nvidia-deep-research"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="current"><meta data-rh="true" name="docusaurus_tag" content="docs-default-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-current"><meta data-rh="true" property="og:title" content="NVIDIA Enterprise RAG and AI-Q Research Assistant on EKS | AI on EKS"><meta data-rh="true" name="description" content="Deployment of Enterprise RAG and AI-Q on EKS requires access to GPU instances (g5, p4, or p5 families). This blueprint relies on Karpenter autoscaling for dynamic GPU provisioning."><meta data-rh="true" property="og:description" content="Deployment of Enterprise RAG and AI-Q on EKS requires access to GPU instances (g5, p4, or p5 families). This blueprint relies on Karpenter autoscaling for dynamic GPU provisioning."><link data-rh="true" rel="icon" href="/ai-on-eks/img/header-icon.png"><link data-rh="true" rel="canonical" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/nvidia-deep-research"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/nvidia-deep-research" hreflang="en"><link data-rh="true" rel="alternate" href="https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/nvidia-deep-research" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Inference on EKS","item":"https://awslabs.github.io/ai-on-eks/docs/category/inference-on-eks"},{"@type":"ListItem","position":2,"name":"GPU Inference on EKS","item":"https://awslabs.github.io/ai-on-eks/docs/category/gpu-inference-on-eks"},{"@type":"ListItem","position":3,"name":"NVIDIA Enterprise RAG and AI-Q Research Assistant on EKS","item":"https://awslabs.github.io/ai-on-eks/docs/blueprints/inference/GPUs/nvidia-deep-research"}]}</script><link rel="stylesheet" href="/ai-on-eks/assets/css/styles.c270b852.css">
77
<script src="/ai-on-eks/assets/js/runtime~main.89d82209.js" defer="defer"></script>
8-
<script src="/ai-on-eks/assets/js/main.981a63f3.js" defer="defer"></script>
8+
<script src="/ai-on-eks/assets/js/main.278e6a60.js" defer="defer"></script>
99
</head>
1010
<body class="navigation-with-keyboard">
1111
<svg style="display: none;"><defs>

0 commit comments

Comments
 (0)