Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"AWS Neuron","local":"aws-neuron","sections":[],"depth":1}"> | |
| <link href="/docs/diffusers/pr_12262/zh/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/entry/start.51af38bc.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/scheduler.5c93273d.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/singletons.2f6324e8.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/index.6d7dc09e.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/paths.5bf4289e.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/entry/app.9a9887bb.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/index.e43dd92b.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/nodes/0.8f6c298a.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/nodes/29.dfc1c276.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/Tip.1cbfe904.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/CodeBlock.6896320e.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/getInferenceSnippets.7d64e4c6.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"AWS Neuron","local":"aws-neuron","sections":[],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="aws-neuron" 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-neuron"><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 Neuron</span></h1> <p data-svelte-h="svelte-10o1brc">Diffusers 功能可在 <a href="https://aws.amazon.com/ec2/instance-types/inf2/" rel="nofollow">AWS Inf2 实例</a>上使用，这些是由 <a href="https://aws.amazon.com/machine-learning/inferentia/" rel="nofollow">Neuron 机器学习加速器</a>驱动的 EC2 实例。这些实例旨在提供更好的计算性能（更高的吞吐量、更低的延迟）和良好的成本效益，使其成为 AWS 用户将扩散模型部署到生产环境的良好选择。</p> <p data-svelte-h="svelte-udgf4g"><a href="https://huggingface.co/docs/optimum-neuron/en/index" rel="nofollow">Optimum Neuron</a> 是 Hugging Face 库与 AWS 加速器之间的接口，包括 AWS <a href="https://aws.amazon.com/machine-learning/trainium/" rel="nofollow">Trainium</a> 和 AWS <a href="https://aws.amazon.com/machine-learning/inferentia/" rel="nofollow">Inferentia</a>。它支持 Diffusers 中的许多功能，并具有类似的 API，因此如果您已经熟悉 Diffusers，学习起来更容易。一旦您创建了 AWS Inf2 实例，请安装 Optimum Neuron。</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 -->python -m pip install --upgrade-strategy eager optimum[neuronx]<!-- HTML_TAG_END --></pre></div> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-1iylva9">我们提供预构建的 <a href="https://aws.amazon.com/marketplace/pp/prodview-gr3e6yiscria2" rel="nofollow">Hugging Face Neuron 深度学习 AMI</a>（DLAMI）和用于 Amazon SageMaker 的 Optimum Neuron 容器。建议正确设置您的环境。</p></div> <p data-svelte-h="svelte-trr0gu">下面的示例演示了如何在 inf2.8xlarge 实例上使用 Stable Diffusion XL 模型生成图像（一旦模型编译完成，您可以切换到更便宜的 inf2.xlarge 实例）。要生成一些图像，请使用 <code>NeuronStableDiffusionXLPipeline</code> 类，该类类似于 Diffusers 中的 <code>StableDiffusionXLPipeline</code> 类。</p> <p data-svelte-h="svelte-1ody1vo">与 Diffusers 不同，您需要将管道中的模型编译为 Neuron 格式，即 <code>.neuron</code>。运行以下命令将模型导出为 <code>.neuron</code> 格式。</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 -->optimum-cli <span class="hljs-built_in">export</span> neuron --model stabilityai/stable-diffusion-xl-base-1.0 \ | |
| --batch_size 1 \ | |
| --height 1024 `<span class="hljs-comment"># 生成图像的高度（像素），例如 768, 1024` \</span> | |
| --width 1024 `<span class="hljs-comment"># 生成图像的宽度（像素），例如 768, 1024` \</span> | |
| --num_images_per_prompt 1 `<span class="hljs-comment"># 每个提示生成的图像数量，默认为 1` \</span> | |
| --auto_cast matmul `<span class="hljs-comment"># 仅转换矩阵乘法操作` \</span> | |
| --auto_cast_type bf16 `<span class="hljs-comment"># 将操作从 FP32 转换为 BF16` \</span> | |
| sd_neuron_xl/<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1nzkau6">现在使用预编译的 SDXL 模型生成一些图像。</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-meta">>>> </span><span class="hljs-keyword">from</span> optimum.neuron <span class="hljs-keyword">import</span> Neu | |
| ronStableDiffusionXLPipeline | |
| <span class="hljs-meta">>>> </span>stable_diffusion_xl = NeuronStableDiffusionXLPipeline.from_pretrained(<span class="hljs-string">"sd_neuron_xl/"</span>) | |
| <span class="hljs-meta">>>> </span>prompt = <span class="hljs-string">"a pig with wings flying in floating US dollar banknotes in the air, skyscrapers behind, warm color palette, muted colors, detailed, 8k"</span> | |
| <span class="hljs-meta">>>> </span>image = stable_diffusion_xl(prompt).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <img src="https://huggingface.co/datasets/Jingya/document_images/resolve/main/optimum/neuron/sdxl_pig.png" width="256" height="256" alt="peggy generated by sdxl on inf2"> <p data-svelte-h="svelte-1bu1s2g">欢迎查看Optimum Neuron <a href="https://huggingface.co/docs/optimum-neuron/en/inference_tutorials/stable_diffusion#generate-images-with-stable-diffusion-models-on-aws-inferentia" rel="nofollow">文档</a>中更多不同用例的指南和示例！</p> <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/neuron.md" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_179ljof = { | |
| assets: "/docs/diffusers/pr_12262/zh", | |
| base: "/docs/diffusers/pr_12262/zh", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/diffusers/pr_12262/zh/_app/immutable/entry/start.51af38bc.js"), | |
| import("/docs/diffusers/pr_12262/zh/_app/immutable/entry/app.9a9887bb.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 29], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 11.9 kB
- Xet hash:
- d8b7f45bcdc86ddf06b819017c02858d83e116ca7f9ba765bab1faad3bac711c
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.