Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / diffusers /v0.43.0 /zh /training /distributed_inference.html
mishig's picture
mishig
download
raw
10.5 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;分布式推理&quot;,&quot;local&quot;:&quot;distributed-inference&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;选择策略&quot;,&quot;local&quot;:&quot;choosing-a-strategy&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
<link href="/docs/diffusers/main/en/_app/immutable/entry/start.0S0_iEoG.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/I9eooN77.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/Bupkjr9f.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/entry/app.CPdOxCbw.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/CyvZ3FS5.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/l0QnnOED.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DnVIJfC5.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/nodes/0.DteTvmQZ.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/CoSrdQax.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/nodes/368.MZuJGICn.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DSPDl1gz.js" rel="modulepreload">
<!--el5ux9--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Distributed inference&quot;,&quot;local&quot;:&quot;distributed-inference&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Choosing a strategy&quot;,&quot;local&quot;:&quot;choosing-a-strategy&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
<link href="/docs/diffusers/main/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: inline-end; margin-inline-start: 10px; display: inline-flex; position: relative; z-index: 10;"><div dir="ltr" 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 dir="auto">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="distributed-inference" 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="#distributed-inference"><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><!---->分布式推理<!----></span></h1><!--]--><!----> <p>分布式推理将工作负载拆分到多个 GPU 上。它有助于在内存中容纳更大的模型，并同时处理更多提示。</p> <p>Diffusers 支持四种策略。每种策略都有各自的指南，本页将帮助你选择其中一种。</p> <!--[1--><h2 class="relative group"><a id="choosing-a-strategy" 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="#choosing-a-strategy"><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><!---->选择策略<!----></span></h2><!--]--><!----> <p>每种策略解决不同的问题，因此请根据限制你的资源选择一种。</p> <table><thead><tr><th>策略</th><th>拆分</th><th>减少</th><th>单个提示词的延迟</th><th>最佳适用场景</th></tr></thead><tbody><tr><td><a href="../optimization/data_parallelism">数据并行</a></td><td>副本之间的提示</td><td>无，因为每个 GPU 都保存一份完整副本</td><td>unchanged</td><td>模型已经适配，并且您拥有许多提示</td></tr><tr><td><a href="../optimization/device_map">device_map</a></td><td>跨设备的组件</td><td>权重内存</td><td>略差</td><td>模型无法容纳，且互连速度较慢</td></tr><tr><td><a href="../optimization/context_parallelism">上下文并行</a></td><td>输入序列</td><td>激活内存</td><td>lower</td><td>序列较长，例如高分辨率图像或视频</td></tr><tr><td><a href="../optimization/tensor_parallelism">张量并行</a></td><td>权重矩阵</td><td>权重内存</td><td>lower</td><td>某个组件的权重无法容纳，且互连速度很快</td></tr></tbody></table> <p>一些实用建议：</p> <ul><li>如果模型本身已经能够装入显存，且你有大量提示词，请使用数据并行。它在不改动模型的情况下，通过增加 GPU 数量来提升吞吐量，同时不会影响单条提示词的延迟。你可以使用 <a href="../optimization/data_parallelism#accelerate">Accelerate</a> 或 <a href="../optimization/data_parallelism#pytorch-distributed">PyTorch Distributed</a> 来配置。</li> <li>如果单个组件的权重无法容纳，请优先尝试张量并行，因为它能同时降低内存占用和延迟。张量并行在每个块边界处都需要通信，因此需要 NVLink 等高速互连。在 PCIe 上，每层的通信开销可能会超过其节省的计算量，此时 <code>device_map</code> 是更好的选择。<code>device_map</code> 还能处理各组件单独来看没问题、但整体规模过大的情况。</li> <li>如果问题出在激活值而非权重上，请使用上下文并行。这有助于处理长序列，例如包含大量帧的大型图像和视频。请从<a href="../optimization/context_parallelism">上下文并行</a>指南中的基准测试中选择一个后端。</li> <li>如果权重和序列都过大，Diffusers 无法对同一模型同时应用张量并行和上下文并行。如果同时传入两个配置，<code>ParallelConfig</code> 会抛出错误，并且无法对已经并行化的模型第二次调用 <code>enable_parallelism</code>。</li></ul> <p><a href="../optimization/xdit">xDiT</a> 和 <a href="../optimization/para_attn">ParaAttention</a> 社区集成提供了它们自己的上下文并行实现。</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/en/training/distributed_inference.md" 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><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
<script>
{
__sveltekit_1qsdbwf = {
base: "/docs/diffusers/main/en",
assets: "/docs/diffusers/main/en"
};
const element = document.currentScript.parentElement;
Promise.all([
import("/docs/diffusers/main/en/_app/immutable/entry/start.0S0_iEoG.js"),
import("/docs/diffusers/main/en/_app/immutable/entry/app.CPdOxCbw.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 368],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
10.5 kB
·
Xet hash:
50d8a818963228a5801257adb776fea8f45154db47962f9134c82e846616e884

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.