diffusers/pr_12403/zh/optimization/habana.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Intel Gaudi&quot;,&quot;local&quot;:&quot;intel-gaudi&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/diffusers/pr_12403/zh/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/entry/start.009fc24b.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/chunks/scheduler.5c93273d.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/chunks/singletons.c5d047c8.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/chunks/index.6d7dc09e.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/chunks/paths.ad38253d.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/entry/app.45dd6b31.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/chunks/index.e43dd92b.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/nodes/0.a6c0e1b8.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/nodes/26.70d5ecf3.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/chunks/CodeBlock.6896320e.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_12403/zh/_app/immutable/chunks/getInferenceSnippets.161194d2.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Intel Gaudi&quot;,&quot;local&quot;:&quot;intel-gaudi&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>   <h1 class="relative group"><a id="intel-gaudi" 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="#intel-gaudi"><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>Intel Gaudi</span></h1> <p data-svelte-h="svelte-mh5zja">Intel Gaudi AI 加速器系列包括 <a href="https://habana.ai/products/gaudi/" rel="nofollow">Intel Gaudi 1</a>、<a href="https://habana.ai/products/gaudi2/" rel="nofollow">Intel Gaudi 2</a> 和 <a href="https://habana.ai/products/gaudi3/" rel="nofollow">Intel Gaudi 3</a>。每台服务器配备 8 个设备，称为 Habana 处理单元 (HPU)，在 Gaudi 3 上提供 128GB 内存，在 Gaudi 2 上提供 96GB 内存，在第一代 Gaudi 上提供 32GB 内存。有关底层硬件架构的更多详细信息，请查看 <a href="https://docs.habana.ai/en/latest/Gaudi_Overview/Gaudi_Architecture.html" rel="nofollow">Gaudi 架构</a> 概述。</p> <p data-svelte-h="svelte-7cd3xk">Diffusers 管道可以利用 HPU 加速，即使管道尚未添加到 <a href="https://huggingface.co/docs/optimum/main/en/habana/index" rel="nofollow">Optimum for Intel Gaudi</a>，也可以通过 <a href="https://docs.habana.ai/en/latest/PyTorch/PyTorch_Model_Porting/GPU_Migration_Toolkit/GPU_Migration_Toolkit.html" rel="nofollow">GPU 迁移工具包</a> 实现。</p> <p data-svelte-h="svelte-1vh47tk">在您的管道上调用 <code>.to(&quot;hpu&quot;)</code> 以将其移动到 HPU 设备，如下所示为 Flux 示例：</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" 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> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;black-forest-labs/FLUX.1-schnell&quot;</span>, torch_dtype=torch.bfloat16)
pipeline.to(<span class="hljs-string">&quot;hpu&quot;</span>)

image = pipeline(<span class="hljs-string">&quot;一张松鼠在毕加索风格中的图像&quot;</span>).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <blockquote class="tip" data-svelte-h="svelte-c1zwav"><p>对于 Gaudi 优化的扩散管道实现，我们推荐使用 <a href="https://huggingface.co/docs/optimum/main/en/habana/index" rel="nofollow">Optimum for Intel Gaudi</a>。</p></blockquote> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/diffusers/blob/main/docs/source/zh/optimization/habana.md" 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_e2f86x = {
						assets: "/docs/diffusers/pr_12403/zh",
						base: "/docs/diffusers/pr_12403/zh",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/diffusers/pr_12403/zh/_app/immutable/entry/start.009fc24b.js"),
						import("/docs/diffusers/pr_12403/zh/_app/immutable/entry/app.45dd6b31.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 26],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>