optimum/pr_2473/en/index.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;🤗 Optimum&quot;,&quot;local&quot;:&quot;-optimum&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Hardware partners&quot;,&quot;local&quot;:&quot;hardware-partners&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Open-source integrations&quot;,&quot;local&quot;:&quot;open-source-integrations&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
		<link href="/docs/optimum/pr_2473/en/_app/immutable/entry/start.d0J1BV66.js" rel="modulepreload">
		<link href="/docs/optimum/pr_2473/en/_app/immutable/chunks/CeVREhC8.js" rel="modulepreload">
		<link href="/docs/optimum/pr_2473/en/_app/immutable/chunks/Ar-ck91Q.js" rel="modulepreload">
		<link href="/docs/optimum/pr_2473/en/_app/immutable/entry/app.DkQe1STU.js" rel="modulepreload">
		<link href="/docs/optimum/pr_2473/en/_app/immutable/chunks/CkE5WS0h.js" rel="modulepreload">
		<link href="/docs/optimum/pr_2473/en/_app/immutable/chunks/DHlwxjpI.js" rel="modulepreload">
		<link href="/docs/optimum/pr_2473/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
		<link href="/docs/optimum/pr_2473/en/_app/immutable/chunks/B3dp56CO.js" rel="modulepreload">
		<link href="/docs/optimum/pr_2473/en/_app/immutable/nodes/0.Ca4AVuFu.js" rel="modulepreload">
		<link href="/docs/optimum/pr_2473/en/_app/immutable/chunks/BZNZRPnR.js" rel="modulepreload">
		<link href="/docs/optimum/pr_2473/en/_app/immutable/nodes/6.BBG8_pcW.js" rel="modulepreload">
		<link href="/docs/optimum/pr_2473/en/_app/immutable/chunks/Ikg18yq4.js" rel="modulepreload">
		<!--1ldsu9f--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;🤗 Optimum&quot;,&quot;local&quot;:&quot;-optimum&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Hardware partners&quot;,&quot;local&quot;:&quot;hardware-partners&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Open-source integrations&quot;,&quot;local&quot;:&quot;open-source-integrations&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
		<link href="/docs/optimum/pr_2473/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><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> <!--[-1--><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="-optimum" 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="#-optimum"><span><svg 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>🤗 Optimum</span></h1><!--]--><!----> <p>🤗 Optimum is an extension of <a href="https://huggingface.co/docs/transformers" rel="nofollow">Transformers</a> that provides a set of performance optimization tools to train and run models on targeted hardware with maximum efficiency.</p> <p>The AI ecosystem evolves quickly, and more and more specialized hardware along with their own optimizations are emerging every day.
As such, Optimum enables developers to efficiently use any of these platforms with the same ease inherent to Transformers.</p> <p>🤗 Optimum is distributed as a collection of packages - check out the links below for an in-depth look at each one.</p> <!--[1--><h2 class="relative group"><a id="hardware-partners" 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="#hardware-partners"><span><svg 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>Hardware partners</span></h2><!--]--><!----> <p>The packages below enable you to get the best of the 🤗 Hugging Face ecosystem on various types of devices.</p> <div class="mt-10"><div class="w-full flex flex-col space-y-4 md:space-y-0 md:grid md:grid-cols-3 md:gap-y-4 md:gap-x-5"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://github.com/huggingface/optimum-nvidia"><div class="w-full text-center bg-gradient-to-br from-green-600 to-green-600 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">NVIDIA</div></a><p class="text-gray-700"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://github.com/huggingface/optimum-nvidia">Accelerate inference with NVIDIA TensorRT-LLM on the</a><a class="underline" href="https://developer.nvidia.com/blog/nvidia-tensorrt-llm-supercharges-large-language-model-inference-on-nvidia-h100-gpus/" target="_blank" rel="noreferrer">NVIDIA platform</a></p> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/docs/optimum-neuron/index"><div class="w-full text-center bg-gradient-to-br from-orange-400 to-orange-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">AWS Trainium/Inferentia</div></a><p class="text-gray-700"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/docs/optimum-neuron/index">Accelerate your training and inference workflows with</a><a class="underline" href="https://aws.amazon.com/machine-learning/trainium/" target="_blank" rel="noreferrer">AWS Trainium</a> and <a class="underline" href="https://aws.amazon.com/machine-learning/inferentia/" target="_blank" rel="noreferrer">AWS Inferentia</a></p> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/docs/optimum-tpu/index"><div class="w-full text-center bg-gradient-to-br from-blue-500 to-blue-600 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Google TPUs</div></a><p class="text-gray-700"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/docs/optimum-tpu/index">Accelerate your training and inference workflows with</a><a class="underline" href="https://cloud.google.com/tpu" target="_blank" rel="noreferrer">Google TPUs</a></p> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/docs/optimum-intel/index"><div class="w-full text-center bg-gradient-to-br from-blue-400 to-blue-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Intel</div></a><p class="text-gray-700"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/docs/optimum-intel/index">Optimize your model to speedup inference with</a><a class="underline" href="https://docs.openvino.ai/2025/index.html" target="_blank" rel="noreferrer">OpenVINO</a></p> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/docs/optimum-habana/index"><div class="w-full text-center bg-gradient-to-br from-indigo-400 to-indigo-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Intel Gaudi</div></a><p class="text-gray-700"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/docs/optimum-habana/index">Maximize training throughput and efficiency with</a><a class="underline" href="https://docs.habana.ai/en/latest/Gaudi_Overview/Gaudi_Architecture.html" target="_blank" rel="noreferrer">Intel's Gaudi processor</a></p> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./furiosa/index"><div class="w-full text-center bg-gradient-to-br from-green-400 to-green-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">FuriosaAI</div></a><p class="text-gray-700"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./furiosa/index">Fast and efficient inference on</a><a class="underline" href="https://www.furiosa.ai/" target="_blank" rel="noreferrer">FuriosaAI WARBOY</a></p></div></div> <!--[1--><h2 class="relative group"><a id="open-source-integrations" 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="#open-source-integrations"><span><svg 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>Open-source integrations</span></h2><!--]--><!----> <p>🤗 Optimum also supports a variety of open-source frameworks to make model optimization very easy.</p> <div class="mt-10"><div class="w-full flex flex-col space-y-4 md:space-y-0 md:grid md:grid-cols-3 md:gap-y-4 md:gap-x-5"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/docs/optimum-onnx/index"><div class="w-full text-center bg-gradient-to-br from-pink-400 to-pink-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">ONNX Runtime</div></a><p class="text-gray-700"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://huggingface.co/docs/optimum-onnx/index">Apply quantization and graph optimization to accelerate Transformers models training and inference with</a><a class="underline" href="https://onnxruntime.ai/" target="_blank" rel="noreferrer">ONNX Runtime</a></p> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://github.com/huggingface/optimum-executorch"><div class="w-full text-center bg-gradient-to-br from-red-500 to-red-600 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">ExecuTorch</div></a><p class="text-gray-700"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="https://github.com/huggingface/optimum-executorch">PyTorch’s native solution to inference on the Edge via</a><a class="underline" href="https://pytorch.org/executorch/stable/" target="_blank" rel="noreferrer">ExecuTorch</a></p> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./exporters/overview"><div class="w-full text-center bg-gradient-to-br from-purple-400 to-purple-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Exporters</div> <p class="text-gray-700">Export your PyTorch model to different formats such as ONNX</p></a> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./torch_fx/overview"><div class="w-full text-center bg-gradient-to-br from-green-400 to-green-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Torch FX</div></a><p class="text-gray-700"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./torch_fx/overview">Create and compose custom graph transformations to optimize PyTorch Transformers models with</a><a class="underline" href="https://pytorch.org/docs/stable/fx.html#" target="_blank" rel="noreferrer">Torch FX</a></p></div></div> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
			
			<script>
				{
					__sveltekit_1uuqce1 = {
						base: "/docs/optimum/pr_2473/en",
						assets: "/docs/optimum/pr_2473/en"
					};

					const element = document.currentScript.parentElement;

					Promise.all([
						import("/docs/optimum/pr_2473/en/_app/immutable/entry/start.d0J1BV66.js"),
						import("/docs/optimum/pr_2473/en/_app/immutable/entry/app.DkQe1STU.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 6],
							data: [null,null],
							form: null,
							error: null
						});
					});
				}
			</script>