optimum-intel/pr_1192/en/index.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;🤗 Optimum Intel&quot;,&quot;local&quot;:&quot;-optimum-intel&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/optimum.intel/pr_1192/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/optimum.intel/pr_1192/en/_app/immutable/entry/start.555e0ad7.js">
		<link rel="modulepreload" href="/docs/optimum.intel/pr_1192/en/_app/immutable/chunks/scheduler.7da89386.js">
		<link rel="modulepreload" href="/docs/optimum.intel/pr_1192/en/_app/immutable/chunks/singletons.b8a6b55e.js">
		<link rel="modulepreload" href="/docs/optimum.intel/pr_1192/en/_app/immutable/chunks/paths.a393af5a.js">
		<link rel="modulepreload" href="/docs/optimum.intel/pr_1192/en/_app/immutable/entry/app.e565aa6a.js">
		<link rel="modulepreload" href="/docs/optimum.intel/pr_1192/en/_app/immutable/chunks/index.20910acc.js">
		<link rel="modulepreload" href="/docs/optimum.intel/pr_1192/en/_app/immutable/nodes/0.56cae30b.js">
		<link rel="modulepreload" href="/docs/optimum.intel/pr_1192/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/optimum.intel/pr_1192/en/_app/immutable/nodes/2.b9929abb.js">
		<link rel="modulepreload" href="/docs/optimum.intel/pr_1192/en/_app/immutable/chunks/EditOnGithub.ba36cbd0.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;🤗 Optimum Intel&quot;,&quot;local&quot;:&quot;-optimum-intel&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>   <h1 class="relative group"><a id="-optimum-intel" 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-intel"><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>🤗 Optimum Intel</span></h1> <p data-svelte-h="svelte-1y6q76e">🤗 Optimum Intel is the interface between the 🤗 Transformers and Diffusers libraries and the different tools and libraries provided by Intel to accelerate end-to-end pipelines on Intel architectures.</p> <p data-svelte-h="svelte-1xbmto8"><a href="https://www.intel.com/content/www/us/en/developer/tools/oneapi/neural-compressor.html" rel="nofollow">Intel Neural Compressor</a> is an open-source library enabling the usage of the most popular compression techniques such as quantization, pruning and knowledge distillation. It supports automatic accuracy-driven tuning strategies in order for users to easily generate quantized model. The users can easily apply static, dynamic and aware-training quantization approaches while giving an expected accuracy criteria. It also supports different weight pruning techniques enabling the creation of pruned model giving a predefined sparsity target.</p> <p data-svelte-h="svelte-6499sz"><a href="https://docs.openvino.ai" rel="nofollow">OpenVINO</a> is an open-source toolkit that enables high performance inference capabilities for Intel CPUs, GPUs, and special DL inference accelerators (<a href="https://docs.openvino.ai/2024/about-openvino/compatibility-and-support/supported-devices.html" rel="nofollow">see</a> the full list of supported devices). It is supplied with a set of tools to optimize your models with compression techniques such as quantization, pruning and knowledge distillation. Optimum Intel provides a simple interface to optimize your Transformers and Diffusers models, convert them to the OpenVINO Intermediate Representation (IR) format and run inference using OpenVINO Runtime.</p> <p data-svelte-h="svelte-ieerj6"><a href="https://intel.github.io/intel-extension-for-pytorch/#introduction" rel="nofollow">Intel Extension for PyTorch</a> (IPEX) is an open-source library which provides optimizations for both eager mode and graph mode, however, compared to eager mode, graph mode in PyTorch* normally yields better performance from optimization techniques, such as operation fusion.</p> <div class="mt-10" data-svelte-h="svelte-3up1bp"><div class="w-full flex flex-col space-x-4 md:grid md:grid-cols-3 md:gap-x-5"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="neural_compressor/optimization"><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">Neural Compressor</div> <p class="text-gray-700">Learn how to apply compression techniques such as quantization, pruning and knowledge distillation to speed up inference.</p></a> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="openvino/export"><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">OpenVINO</div> <p class="text-gray-700">Learn how to run inference with OpenVINO Runtime and to apply quantization to further speed up inference.</p></a> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="ipex/inference"><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">IPEX</div> <p class="text-gray-700">Learn how to optimize your model with IPEX.</p></a></div></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/optimum-intel/blob/main/docs/source/index.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_kqgmcb = {
						assets: "/docs/optimum.intel/pr_1192/en",
						base: "/docs/optimum.intel/pr_1192/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/optimum.intel/pr_1192/en/_app/immutable/entry/start.555e0ad7.js"),
						import("/docs/optimum.intel/pr_1192/en/_app/immutable/entry/app.e565aa6a.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 2],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>