hugs/pr_15/en/hardware.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Supported Hardware Providers&quot;,&quot;local&quot;:&quot;supported-hardware-providers&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;NVIDIA GPUs&quot;,&quot;local&quot;:&quot;nvidia-gpus&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;AMD GPUs&quot;,&quot;local&quot;:&quot;amd-gpus&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;AWS Accelerators (Inferentia/Trainium)&quot;,&quot;local&quot;:&quot;aws-accelerators-inferentiatrainium&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Google TPUs&quot;,&quot;local&quot;:&quot;google-tpus&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/hugs/pr_15/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/hugs/pr_15/en/_app/immutable/entry/start.1eb801dd.js">
		<link rel="modulepreload" href="/docs/hugs/pr_15/en/_app/immutable/chunks/scheduler.6efaaf90.js">
		<link rel="modulepreload" href="/docs/hugs/pr_15/en/_app/immutable/chunks/singletons.292a6ba8.js">
		<link rel="modulepreload" href="/docs/hugs/pr_15/en/_app/immutable/chunks/paths.abf024ca.js">
		<link rel="modulepreload" href="/docs/hugs/pr_15/en/_app/immutable/entry/app.30f95b8f.js">
		<link rel="modulepreload" href="/docs/hugs/pr_15/en/_app/immutable/chunks/preload-helper.c27256c5.js">
		<link rel="modulepreload" href="/docs/hugs/pr_15/en/_app/immutable/chunks/index.eb3e1f0f.js">
		<link rel="modulepreload" href="/docs/hugs/pr_15/en/_app/immutable/nodes/0.8980f070.js">
		<link rel="modulepreload" href="/docs/hugs/pr_15/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/hugs/pr_15/en/_app/immutable/nodes/6.8e920941.js">
		<link rel="modulepreload" href="/docs/hugs/pr_15/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.c5737ce8.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Supported Hardware Providers&quot;,&quot;local&quot;:&quot;supported-hardware-providers&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;NVIDIA GPUs&quot;,&quot;local&quot;:&quot;nvidia-gpus&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;AMD GPUs&quot;,&quot;local&quot;:&quot;amd-gpus&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;AWS Accelerators (Inferentia/Trainium)&quot;,&quot;local&quot;:&quot;aws-accelerators-inferentiatrainium&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Google TPUs&quot;,&quot;local&quot;:&quot;google-tpus&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div>  <h1 class="relative group"><a id="supported-hardware-providers" 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="#supported-hardware-providers"><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>Supported Hardware Providers</span></h1> <p data-svelte-h="svelte-o0d4dl">HUGS are optimized for a wide-variety of accelerators for ML inference, and support across different accelerator families and providers will continue to grow exponentially.</p>  <h2 class="relative group"><a id="nvidia-gpus" 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="#nvidia-gpus"><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>NVIDIA GPUs</span></h2> <p data-svelte-h="svelte-1eptsmk">NVIDIA GPUs are widely used for machine learning and AI applications, offering high performance and specialized hardware for deep learning tasks. NVIDIA’s CUDA platform provides a robust ecosystem for GPU-accelerated computing.</p> <p data-svelte-h="svelte-r710j6">Supported device(s):</p> <ul data-svelte-h="svelte-1xy7gow"><li><strong>NVIDIA A10G</strong>: 24GB GDDR6 memory, 9216 CUDA cores, 288 Tensor cores, 72 RT cores</li> <li><strong>NVIDIA L4</strong>: 24GB GDDR6 memory, 7168 CUDA cores, 224 Tensor cores, 56 RT cores</li> <li><strong>NVIDIA L40S</strong>: 48GB GDDR6 memory, 18176 CUDA cores, 568 Tensor cores, 142 RT cores</li> <li><strong>NVIDIA A100</strong>: 40/80GB HBM2e memory, 6912 CUDA cores, 432 Tensor cores, 108 RT cores</li> <li><strong>NVIDIA H100</strong>: 80GB HBM3 memory, 14592 CUDA cores, 456 Tensor cores, 144 RT cores</li></ul>  <h2 class="relative group"><a id="amd-gpus" 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="#amd-gpus"><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>AMD GPUs</span></h2> <p data-svelte-h="svelte-1id81yq">AMD GPUs provide strong competition in the AI and machine learning space, offering high-performance computing capabilities with their CDNA architecture. AMD’s ROCm (Radeon Open Compute) platform enables GPU-accelerated computing on Linux systems.</p> <p data-svelte-h="svelte-r710j6">Supported device(s):</p> <ul data-svelte-h="svelte-kswfo6"><li><strong>AMD Instinct MI300X</strong>: 192GB HBM3 memory, 304 Compute Units, 4864 AI Accelerators</li></ul>  <h2 class="relative group"><a id="aws-accelerators-inferentiatrainium" 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="#aws-accelerators-inferentiatrainium"><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>AWS Accelerators (Inferentia/Trainium)</span></h2> <p data-svelte-h="svelte-1tni5e8">AWS Inferentia2 is a custom-built accelerator designed specifically for high-performance, cost-effective machine learning inference.</p> <p data-svelte-h="svelte-r710j6">Supported device(s):</p> <ul data-svelte-h="svelte-7jaagk"><li><strong>AWS Inferentia2</strong>: Available in Amazon EC2 Inf2 instances, offering up to 12 Inferentia2 chips per instance. AWS Inferentia2 accelerators are optimized for deploying large language models and other compute-intensive ML workloads, providing high throughput and low latency for inference tasks. More information at <a href="https://aws.amazon.com/ec2/instance-types/inf2" rel="nofollow">Amazon EC2 Inf2 Instances</a>.</li> <li><strong>AWS Trainium</strong>: <em>Coming soon!</em></li></ul>  <h2 class="relative group"><a id="google-tpus" 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="#google-tpus"><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>Google TPUs</span></h2> <p data-svelte-h="svelte-b65gt3"><em>Coming soon</em></p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/hugs-docs/blob/main/docs/source/hardware.mdx" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_1jpg4vp = {
						assets: "/docs/hugs/pr_15/en",
						base: "/docs/hugs/pr_15/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/hugs/pr_15/en/_app/immutable/entry/start.1eb801dd.js"),
						import("/docs/hugs/pr_15/en/_app/immutable/entry/app.30f95b8f.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 6],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>