optimum-neuron/v0.2.0.dev2/en/guides/sagemaker.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Using Optimum Neuron on Amazon SageMaker&quot;,&quot;local&quot;:&quot;using-optimum-neuron-on-amazon-sagemaker&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Deploy Embedding Models on Inferentia2 for Efficient Similarity Search&quot;,&quot;local&quot;:&quot;deploy-embedding-models-on-inferentia2-for-efficient-similarity-search&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Deploy Llama 2 7B on AWS inferentia2 with Amazon SageMaker&quot;,&quot;local&quot;:&quot;deploy-llama-2-7b-on-aws-inferentia2-with-amazon-sagemaker&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Deploy Stable Diffusion XL on AWS inferentia2 with Amazon SageMaker&quot;,&quot;local&quot;:&quot;deploy-stable-diffusion-xl-on-aws-inferentia2-with-amazon-sagemaker&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Deploy BERT for Text Classification on AWS inferentia2 with Amazon SageMaker&quot;,&quot;local&quot;:&quot;deploy-bert-for-text-classification-on-aws-inferentia2-with-amazon-sagemaker&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/entry/start.c3692dcd.js">
		<link rel="modulepreload" href="/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/chunks/scheduler.85c25b89.js">
		<link rel="modulepreload" href="/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/chunks/singletons.bf318e21.js">
		<link rel="modulepreload" href="/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/chunks/paths.4f2bc42b.js">
		<link rel="modulepreload" href="/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/entry/app.40ef12d9.js">
		<link rel="modulepreload" href="/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/chunks/index.c9bcf812.js">
		<link rel="modulepreload" href="/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/nodes/0.8386078c.js">
		<link rel="modulepreload" href="/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/nodes/12.e6a00439.js">
		<link rel="modulepreload" href="/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/chunks/index.9790a2b6.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Using Optimum Neuron on Amazon SageMaker&quot;,&quot;local&quot;:&quot;using-optimum-neuron-on-amazon-sagemaker&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Deploy Embedding Models on Inferentia2 for Efficient Similarity Search&quot;,&quot;local&quot;:&quot;deploy-embedding-models-on-inferentia2-for-efficient-similarity-search&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Deploy Llama 2 7B on AWS inferentia2 with Amazon SageMaker&quot;,&quot;local&quot;:&quot;deploy-llama-2-7b-on-aws-inferentia2-with-amazon-sagemaker&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Deploy Stable Diffusion XL on AWS inferentia2 with Amazon SageMaker&quot;,&quot;local&quot;:&quot;deploy-stable-diffusion-xl-on-aws-inferentia2-with-amazon-sagemaker&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Deploy BERT for Text Classification on AWS inferentia2 with Amazon SageMaker&quot;,&quot;local&quot;:&quot;deploy-bert-for-text-classification-on-aws-inferentia2-with-amazon-sagemaker&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>   <h1 class="relative group"><a id="using-optimum-neuron-on-amazon-sagemaker" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#using-optimum-neuron-on-amazon-sagemaker"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Using Optimum Neuron on Amazon SageMaker</span></h1> <p data-svelte-h="svelte-13cd18f"><a href="https://github.com/huggingface/optimum-neuron" rel="nofollow">Optimum Neuron</a> is integrated into Amazon SageMaker through the Hugging Face Deep Learning Containers for AWS Accelerators like Inferentia2 and Trainium1. This allows you to easily train and deploy 🤗 Transformers and Diffusers models on Amazon SageMaker leveraging AWS accelerators.</p> <p data-svelte-h="svelte-1ngzo57">The Hugging Face DLC images come with pre-installed Optimum Neuron and tools to compile models for efficient inference on Inferentia2 and Trainium1. This makes deploying large transformer models simple and optimized out of the box.</p> <p data-svelte-h="svelte-16q6ucs">Below is a list of available end-to-end tutorials on using Optimum Neuron via the Hugging Face DLC to train and deploy models on Amazon SageMaker. Follow the end-to-end examples to learn how Optimum Neuron integrates with SageMaker through the Hugging Face DLC images to unlock performance and cost benefits.</p>  <h2 class="relative group"><a id="deploy-embedding-models-on-inferentia2-for-efficient-similarity-search" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#deploy-embedding-models-on-inferentia2-for-efficient-similarity-search"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Deploy Embedding Models on Inferentia2 for Efficient Similarity Search</span></h2> <p data-svelte-h="svelte-1utk3kr">Tutorial on how to deploy a text embedding model (BGE-Base) for efficient and fast embedding generation on AWS Inferentia2 using Amazon SageMaker; The post shows how Inferentia2 can be a great option for not only efficient and fast but also cost-effective inference of embeddings compared to GPUs or services like OpenAI and Amazon Bedrock.</p> <ul data-svelte-h="svelte-1n73dx9"><li><a href="https://www.philschmid.de/inferentia2-embeddings" rel="nofollow">Tutorial</a></li> <li><a href="https://github.com/philschmid/huggingface-inferentia2-samples/blob/main/llama2-7b/sagemaker-notebook.ipynb" rel="nofollow">GitHub Repo</a></li></ul>  <h2 class="relative group"><a id="deploy-llama-2-7b-on-aws-inferentia2-with-amazon-sagemaker" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#deploy-llama-2-7b-on-aws-inferentia2-with-amazon-sagemaker"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Deploy Llama 2 7B on AWS inferentia2 with Amazon SageMaker</span></h2> <p data-svelte-h="svelte-1dii1xw">Tutorial on how to deploy the conversational Llama 2 model on AWS Inferentia2 using Amazon SageMaker for low-latency inference; Shows how to leverage Inferentia2 and SageMaker to go from model training to production deployment with just a few lines of code.</p> <ul data-svelte-h="svelte-1lzr929"><li><a href="https://www.philschmid.de/inferentia2-llama-7b" rel="nofollow">Tutorial</a></li> <li><a href="https://github.com/philschmid/huggingface-inferentia2-samples/blob/main/stable-diffusion-xl/sagemaker-notebook.ipynb" rel="nofollow">GitHub Repo</a></li></ul>  <h2 class="relative group"><a id="deploy-stable-diffusion-xl-on-aws-inferentia2-with-amazon-sagemaker" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#deploy-stable-diffusion-xl-on-aws-inferentia2-with-amazon-sagemaker"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Deploy Stable Diffusion XL on AWS inferentia2 with Amazon SageMaker</span></h2> <p data-svelte-h="svelte-18imwet">Tutorial on how to deploy Stable Diffusion XL model on AWS Inferentia2 using Optimum Neuron and Amazon SageMaker for efficient 1024x1024 image generation achieving ~6 seconds per image; The post shows how a single <code>inf2.xlarge</code> instance costing $0.99/hour can achieve ~10 images per minute, making Inferentia2 a great option for not only efficient and fast but also cost-effective inference of images compared to GPUs.</p> <ul data-svelte-h="svelte-9jfujr"><li><a href="https://www.philschmid.de/inferentia2-stable-diffusion-xl" rel="nofollow">Tutorial</a></li> <li><a href="https://github.com/Placeholder/stable-diffusion-inferentia" rel="nofollow">GitHub Repo</a></li></ul>  <h2 class="relative group"><a id="deploy-bert-for-text-classification-on-aws-inferentia2-with-amazon-sagemaker" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#deploy-bert-for-text-classification-on-aws-inferentia2-with-amazon-sagemaker"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Deploy BERT for Text Classification on AWS inferentia2 with Amazon SageMaker</span></h2> <p data-svelte-h="svelte-1a6nhs6">Tutorial on how to optimize and deploy BERT model on AWS Inferentia2 using Optimum Neuron and Amazon SageMaker for efficient text classification achieving 4ms latency; The post shows how a single inf2.xlarge instance costing $0.99/hour can achieve 116 inferences/sec and 500 inferences/sec without network overhead, making Inferentia2 a great option for low-latency and cost-effective inference compared to GPUs.</p> <ul data-svelte-h="svelte-15612wl"><li><a href="https://www.philschmid.de/optimize-deploy-bert-inf2" rel="nofollow">Tutorial</a></li> <li><a href="https://github.com/philschmid/huggingface-inferentia2-samples/blob/main/bert-transformers/sagemaker-notebook.ipynb" rel="nofollow">GitHub Repo</a></li></ul>  <p></p> 
			
			<script>
				{
					__sveltekit_1eimgpm = {
						assets: "/docs/optimum.neuron/v0.2.0.dev2/en",
						base: "/docs/optimum.neuron/v0.2.0.dev2/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/entry/start.c3692dcd.js"),
						import("/docs/optimum.neuron/v0.2.0.dev2/en/_app/immutable/entry/app.40ef12d9.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 12],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>