Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / diffusers /pr_12652 /zh /optimization /tome.html
download
raw
17.4 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;令牌合并&quot;,&quot;local&quot;:&quot;令牌合并&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;基准测试&quot;,&quot;local&quot;:&quot;基准测试&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
 <link href="/docs/diffusers/pr_12652/zh/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/entry/start.ca7a833f.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/scheduler.e4ff9b64.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/singletons.71526a34.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/index.f9be34a7.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/paths.0df57e7f.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/entry/app.746b83f3.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/preload-helper.bb94e341.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/index.09f1bca0.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/nodes/0.8237e20e.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/nodes/36.e5b142a2.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.3bffcf96.js">
 <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/CodeBlock.3dd9a65d.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;令牌合并&quot;,&quot;local&quot;:&quot;令牌合并&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;基准测试&quot;,&quot;local&quot;:&quot;基准测试&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <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> </div> <h1 class="relative group"><a id="令牌合并" 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="#令牌合并"><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>令牌合并</span></h1> <p data-svelte-h="svelte-snw6ty"><a href="https://huggingface.co/papers/2303.17604" rel="nofollow">令牌合并</a>（ToMe）在基于 Transformer 的网络的前向传递中逐步合并冗余令牌/补丁，这可以加速 <code>StableDiffusionPipeline</code> 的推理延迟。</p> <p data-svelte-h="svelte-7kc1oz">从 <code>pip</code> 安装 ToMe：</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 -->pip install tomesd<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-s9hu2t">您可以使用 <a href="https://github.com/dbolya/tomesd" rel="nofollow"><code>tomesd</code></a> 库中的 <a href="https://github.com/dbolya/tomesd?tab=readme-ov-file#usage" rel="nofollow"><code>apply_patch</code></a> 函数：</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 --> from diffusers import StableDiffusionPipeline
 import torch
 import tomesd
pipeline = StableDiffusionPipeline.from_pretrained(
 &quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;, torch_dtype=torch.float16, use_safetensors=True,
 ).to(&quot;cuda&quot;)
<span class="hljs-addition">+ tomesd.apply_patch(pipeline, ratio=0.5)</span>
image = pipeline(&quot;a photo of an astronaut riding a horse on mars&quot;).images[0]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-om2tu0"><code>apply_patch</code> 函数公开了多个<a href="https://github.com/dbolya/tomesd#usage" rel="nofollow">参数</a>，以帮助在管道推理速度和生成令牌的质量之间取得平衡。最重要的参数是 <code>ratio</code>，它控制在前向传递期间合并的令牌数量。</p> <p data-svelte-h="svelte-1dgeizi">如<a href="https://huggingface.co/papers/2303.17604" rel="nofollow">论文</a>中所述，ToMe 可以在显著提升推理速度的同时，很大程度上保留生成图像的质量。通过增加 <code>ratio</code>，您可以进一步加速推理，但代价是图像质量有所下降。</p> <p data-svelte-h="svelte-mpit8s">为了测试生成图像的质量，我们从 <a href="https://parti.research.google/" rel="nofollow">Parti Prompts</a> 中采样了一些提示，并使用 <code>StableDiffusionPipeline</code> 进行了推理，设置如下：</p> <div class="flex justify-center" data-svelte-h="svelte-ng3g1s"><img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/tome/tome_samples.png"></div> <p data-svelte-h="svelte-za0786">我们没有注意到生成样本的质量有任何显著下降，您可以在此 <a href="https://wandb.ai/sayakpaul/tomesd-results/runs/23j4bj3i?workspace=" rel="nofollow">WandB 报告</a>中查看生成的样本。如果您有兴趣重现此实验，请使用此<a href="https://gist.github.com/sayakpaul/8cac98d7f22399085a060992f411ecbd" rel="nofollow">脚本</a>。</p> <h2 class="relative group"><a id="基准测试" 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="#基准测试"><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>基准测试</span></h2> <p data-svelte-h="svelte-1glgh8p">我们还在启用 <a href="https://huggingface.co/docs/diffusers/optimization/xformers" rel="nofollow">xFormers</a> 的情况下，对 <code>StableDiffusionPipeline</code> 上 <code>tomesd</code> 的影响进行了基准测试，涵盖了多个图像分辨率。结果
结果是从以下开发环境中的A100和V100 GPU获得的：</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 -->- `diffusers` 版本：0.15.1
- Python 版本：3.8.16
- PyTorch 版本（GPU？）：1.13.1+cu116 (True)
- Huggingface_hub 版本：0.13.2
- Transformers 版本：4.27.2
- Accelerate 版本：0.18.0
- xFormers 版本：0.0.16
- tomesd 版本：0.1.2<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-15l389v">要重现此基准测试，请随意使用此<a href="https://gist.github.com/sayakpaul/27aec6bca7eb7b0e0aa4112205850335" rel="nofollow">脚本</a>。结果以秒为单位报告，并且在适用的情况下，我们报告了使用ToMe和ToMe + xFormers时相对于原始管道的加速百分比。</p> <table data-svelte-h="svelte-9agb9s"><thead><tr><th><strong>GPU</strong></th> <th><strong>分辨率</strong></th> <th><strong>批处理大小</strong></th> <th><strong>原始</strong></th> <th><strong>ToMe</strong></th> <th><strong>ToMe + xFormers</strong></th></tr></thead> <tbody><tr><td><strong>A100</strong></td> <td>512</td> <td>10</td> <td>6.88</td> <td>5.26 (+23.55%)</td> <td>4.69 (+31.83%)</td></tr> <tr><td></td> <td>768</td> <td>10</td> <td>OOM</td> <td>14.71</td> <td>11</td></tr> <tr><td></td> <td></td> <td>8</td> <td>OOM</td> <td>11.56</td> <td>8.84</td></tr> <tr><td></td> <td></td> <td>4</td> <td>OOM</td> <td>5.98</td> <td>4.66</td></tr> <tr><td></td> <td></td> <td>2</td> <td>4.99</td> <td>3.24 (+35.07%)</td> <td>2.1 (+37.88%)</td></tr> <tr><td></td> <td></td> <td>1</td> <td>3.29</td> <td>2.24 (+31.91%)</td> <td>2.03 (+38.3%)</td></tr> <tr><td></td> <td>1024</td> <td>10</td> <td>OOM</td> <td>OOM</td> <td>OOM</td></tr> <tr><td></td> <td></td> <td>8</td> <td>OOM</td> <td>OOM</td> <td>OOM</td></tr> <tr><td></td> <td></td> <td>4</td> <td>OOM</td> <td>12.51</td> <td>9.09</td></tr> <tr><td></td> <td></td> <td>2</td> <td>OOM</td> <td>6.52</td> <td>4.96</td></tr> <tr><td></td> <td></td> <td>1</td> <td>6.4</td> <td>3.61 (+43.59%)</td> <td>2.81 (+56.09%)</td></tr> <tr><td><strong>V100</strong></td> <td>512</td> <td>10</td> <td>OOM</td> <td>10.03</td> <td>9.29</td></tr> <tr><td></td> <td></td> <td>8</td> <td>OOM</td> <td>8.05</td> <td>7.47</td></tr> <tr><td></td> <td></td> <td>4</td> <td>5.7</td> <td>4.3 (+24.56%)</td> <td>3.98 (+30.18%)</td></tr> <tr><td></td> <td></td> <td>2</td> <td>3.14</td> <td>2.43 (+22.61%)</td> <td>2.27 (+27.71%)</td></tr> <tr><td></td> <td></td> <td>1</td> <td>1.88</td> <td>1.57 (+16.49%)</td> <td>1.57 (+16.49%)</td></tr> <tr><td></td> <td>768</td> <td>10</td> <td>OOM</td> <td>OOM</td> <td>23.67</td></tr> <tr><td></td> <td></td> <td>8</td> <td>OOM</td> <td>OOM</td> <td>18.81</td></tr> <tr><td></td> <td></td> <td>4</td> <td>OOM</td> <td>11.81</td> <td>9.7</td></tr> <tr><td></td> <td></td> <td>2</td> <td>OOM</td> <td>6.27</td> <td>5.2</td></tr> <tr><td></td> <td></td> <td>1</td> <td>5.43</td> <td>3.38 (+37.75%)</td> <td>2.82 (+48.07%)</td></tr> <tr><td></td> <td>1024</td> <td>10</td> <td>OOM</td> <td></td> <td></td></tr></tbody></table> <p data-svelte-h="svelte-1nf0h2i">如上表所示，<code>tomesd</code> 带来的加速效果在更大的图像分辨率下变得更加明显。有趣的是，使用 <code>tomesd</code> 可以在更高分辨率如 1024x1024 上运行管道。您可能还可以通过 <a href="fp16#torchcompile"><code>torch.compile</code></a> 进一步加速推理。</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/tome.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 data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p>
<script>
 {
 __sveltekit_oaf0l2 = {
 assets: "/docs/diffusers/pr_12652/zh",
 base: "/docs/diffusers/pr_12652/zh",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/diffusers/pr_12652/zh/_app/immutable/entry/start.ca7a833f.js"),
 import("/docs/diffusers/pr_12652/zh/_app/immutable/entry/app.746b83f3.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 36],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
17.4 kB
·
Xet hash:
5815321da509f09eab99e1e0c7c96cb654dcfb84fc34329f66e40d8af25c99ad

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