Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Pruna","local":"pruna","sections":[{"title":"安装","local":"安装","sections":[],"depth":2},{"title":"优化 Diffusers 模型","local":"优化-diffusers-模型","sections":[],"depth":2},{"title":"评估和基准测试Diffusers模型","local":"评估和基准测试diffusers模型","sections":[],"depth":2},{"title":"参考","local":"参考","sections":[],"depth":2}],"depth":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/33.ebd58217.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"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/HfOption.44827c7f.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Pruna","local":"pruna","sections":[{"title":"安装","local":"安装","sections":[],"depth":2},{"title":"优化 Diffusers 模型","local":"优化-diffusers-模型","sections":[],"depth":2},{"title":"评估和基准测试Diffusers模型","local":"评估和基准测试diffusers模型","sections":[],"depth":2},{"title":"参考","local":"参考","sections":[],"depth":2}],"depth":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="pruna" 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="#pruna"><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>Pruna</span></h1> <p data-svelte-h="svelte-14zuif9"><a href="https://github.com/PrunaAI/pruna" rel="nofollow">Pruna</a> 是一个模型优化框架，提供多种优化方法——量化、剪枝、缓存、编译——以加速推理并减少内存使用。以下是优化方法的概览。</p> <table data-svelte-h="svelte-1870rsx"><thead><tr><th>技术</th> <th>描述</th> <th align="center">速度</th> <th align="center">内存</th> <th align="center">质量</th></tr></thead> <tbody><tr><td><code>batcher</code></td> <td>将多个输入分组在一起同时处理，提高计算效率并减少处理时间。</td> <td align="center">✅</td> <td align="center">❌</td> <td align="center">➖</td></tr> <tr><td><code>cacher</code></td> <td>存储计算的中间结果以加速后续操作。</td> <td align="center">✅</td> <td align="center">➖</td> <td align="center">➖</td></tr> <tr><td><code>compiler</code></td> <td>为特定硬件优化模型指令。</td> <td align="center">✅</td> <td align="center">➖</td> <td align="center">➖</td></tr> <tr><td><code>distiller</code></td> <td>训练一个更小、更简单的模型来模仿一个更大、更复杂的模型。</td> <td align="center">✅</td> <td align="center">✅</td> <td align="center">❌</td></tr> <tr><td><code>quantizer</code></td> <td>降低权重和激活的精度，减少内存需求。</td> <td align="center">✅</td> <td align="center">✅</td> <td align="center">❌</td></tr> <tr><td><code>pruner</code></td> <td>移除不重要或冗余的连接和神经元，产生一个更稀疏、更高效的网络。</td> <td align="center">✅</td> <td align="center">✅</td> <td align="center">❌</td></tr> <tr><td><code>recoverer</code></td> <td>在压缩后恢复模型的性能。</td> <td align="center">➖</td> <td align="center">➖</td> <td align="center">✅</td></tr> <tr><td><code>factorizer</code></td> <td>将多个小矩阵乘法批处理为一个大型融合操作。</td> <td align="center">✅</td> <td align="center">➖</td> <td align="center">➖</td></tr> <tr><td><code>enhancer</code></td> <td>通过应用后处理算法（如去噪或上采样）来增强模型输出。</td> <td align="center">❌</td> <td align="center">-</td> <td align="center">✅</td></tr></tbody></table> <p data-svelte-h="svelte-1syz01b">✅ (改进), ➖ (大致相同), ❌ (恶化)</p> <p data-svelte-h="svelte-uq0kan">在 <a href="https://docs.pruna.ai/en/stable/docs_pruna/user_manual/configure.html#configure-algorithms" rel="nofollow">Pruna 文档</a> 中探索所有优化方法。</p> <h2 class="relative group"><a id="安装" 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="#安装"><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>安装</span></h2> <p data-svelte-h="svelte-1g5o862">使用以下命令安装 Pruna。</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 pruna<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="优化-diffusers-模型" 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="#优化-diffusers-模型"><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>优化 Diffusers 模型</span></h2> <p data-svelte-h="svelte-1oye83w">Diffusers 模型支持广泛的优化算法，如下所示。</p> <div class="flex justify-center" data-svelte-h="svelte-1uhmbha"><img src="https://huggingface.co/datasets/PrunaAI/documentation-images/resolve/main/diffusers/diffusers_combinations.png" alt="Diffusers 模型支持的优化算法概览"></div> <p data-svelte-h="svelte-1bmdjcc">下面的示例使用 factorizer、compiler 和 cacher 算法的组合优化 <a href="https://huggingface.co/black-forest-labs/FLUX.1-dev" rel="nofollow">black-forest-labs/FLUX.1-dev</a>。这种组合将推理速度加速高达 4.2 倍，并将峰值 GPU 内存使用从 34.7GB 减少到 28.0GB，同时几乎保持相同的输出质量。</p> <blockquote class="tip" data-svelte-h="svelte-137yx3g"><p>参考 <a href="https://docs.pruna.ai/en/stable/docs_pruna/user_manual/configure.html" rel="nofollow">Pruna 优化</a> 文档以了解更多关于该操作的信息。 | |
| 本示例中使用的优化技术。</p></blockquote> <div class="flex justify-center" data-svelte-h="svelte-1yaafaz"><img src="https://huggingface.co/datasets/PrunaAI/documentation-images/resolve/main/diffusers/flux_combination.png" alt="用于FLUX.1-dev的优化技术展示，结合了因子分解器、编译器和缓存器算法"></div> <p data-svelte-h="svelte-146qhef">首先定义一个包含要使用的优化算法的<code>SmashConfig</code>。要优化模型，将管道和<code>SmashConfig</code>用<code>smash</code>包装，然后像往常一样使用管道进行推理。</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> FluxPipeline | |
| <span class="hljs-keyword">from</span> pruna <span class="hljs-keyword">import</span> PrunaModel, SmashConfig, smash | |
| <span class="hljs-comment"># 加载模型</span> | |
| <span class="hljs-comment"># 使用小GPU内存尝试segmind/Segmind-Vega或black-forest-labs/FLUX.1-schnell</span> | |
| pipe = FluxPipeline.from_pretrained( | |
| <span class="hljs-string">"black-forest-labs/FLUX.1-dev"</span>, | |
| torch_dtype=torch.bfloat16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| <span class="hljs-comment"># 定义配置</span> | |
| smash_config = SmashConfig() | |
| smash_config[<span class="hljs-string">"factorizer"</span>] = <span class="hljs-string">"qkv_diffusers"</span> | |
| smash_config[<span class="hljs-string">"compiler"</span>] = <span class="hljs-string">"torch_compile"</span> | |
| smash_config[<span class="hljs-string">"torch_compile_target"</span>] = <span class="hljs-string">"module_list"</span> | |
| smash_config[<span class="hljs-string">"cacher"</span>] = <span class="hljs-string">"fora"</span> | |
| smash_config[<span class="hljs-string">"fora_interval"</span>] = <span class="hljs-number">2</span> | |
| <span class="hljs-comment"># 为了获得最佳速度结果，可以添加这些配置</span> | |
| <span class="hljs-comment"># 但它们会将预热时间从1.5分钟增加到10分钟</span> | |
| <span class="hljs-comment"># smash_config["torch_compile_mode"] = "max-autotune-no-cudagraphs"</span> | |
| <span class="hljs-comment"># smash_config["quantizer"] = "torchao"</span> | |
| <span class="hljs-comment"># smash_config["torchao_quant_type"] = "fp8dq"</span> | |
| <span class="hljs-comment"># smash_config["torchao_excluded_modules"] = "norm+embedding"</span> | |
| <span class="hljs-comment"># 优化模型</span> | |
| smashed_pipe = smash(pipe, smash_config) | |
| <span class="hljs-comment"># 运行模型</span> | |
| smashed_pipe(<span class="hljs-string">"a knitted purple prune"</span>).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-1or519q"><img src="https://huggingface.co/datasets/PrunaAI/documentation-images/resolve/main/diffusers/flux_smashed_comparison.png"></div> <p data-svelte-h="svelte-1yw57hm">优化后，我们可以使用Hugging Face Hub共享和加载优化后的模型。</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-comment"># 保存模型</span> | |
| smashed_pipe.save_to_hub(<span class="hljs-string">"<username>/FLUX.1-dev-smashed"</span>) | |
| <span class="hljs-comment"># 加载模型</span> | |
| smashed_pipe = PrunaModel.from_hub(<span class="hljs-string">"<username>/FLUX.1-dev-smashed"</span>)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="评估和基准测试diffusers模型" 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="#评估和基准测试diffusers模型"><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>评估和基准测试Diffusers模型</span></h2> <p data-svelte-h="svelte-ufsph6">Pruna提供了<a href="https://docs.pruna.ai/en/stable/docs_pruna/user_manual/evaluate.html" rel="nofollow">EvaluationAgent</a>来评估优化后模型的质量。</p> <p data-svelte-h="svelte-76s5k8">我们可以定义我们关心的指标，如总时间和吞吐量，以及要评估的数据集。我们可以定义一个模型并将其传递给<code>EvaluationAgent</code>。</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white">optimized model </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm">standalone model </div></div> <div class="language-select"><p data-svelte-h="svelte-1wfu4ax">我们可以通过使用<code>EvaluationAgent</code>加载和评估优化后的模型，并将其传递给<code>Task</code>。</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> FluxPipeline | |
| <span class="hljs-keyword">from</span> pruna <span class="hljs-keyword">import</span> PrunaModel | |
| <span class="hljs-keyword">from</span> pruna.data.pruna_datamodule <span class="hljs-keyword">import</span> PrunaDataModule | |
| <span class="hljs-keyword">from</span> pruna.evaluation.evaluation_agent <span class="hljs-keyword">import</span> EvaluationAgent | |
| <span class="hljs-keyword">from</span> pruna.evaluation.metrics <span class="hljs-keyword">import</span> ( | |
| ThroughputMetric, | |
| TorchMetricWrapper, | |
| TotalTimeMetric, | |
| ) | |
| <span class="hljs-keyword">from</span> pruna.evaluation.task <span class="hljs-keyword">import</span> Task | |
| <span class="hljs-comment"># define the device</span> | |
| device = <span class="hljs-string">"cuda"</span> <span class="hljs-keyword">if</span> torch.cuda.is_available() <span class="hljs-keyword">else</span> <span class="hljs-string">"mps"</span> <span class="hljs-keyword">if</span> torch.backends.mps.is_available() <span class="hljs-keyword">else</span> <span class="hljs-string">"cpu"</span> | |
| <span class="hljs-comment"># 加载模型</span> | |
| <span class="hljs-comment"># 使用小GPU内存尝试 PrunaAI/Segmind-Vega-smashed 或 PrunaAI/FLUX.1-dev-smashed</span> | |
| smashed_pipe = PrunaModel.from_hub(<span class="hljs-string">"PrunaAI/FLUX.1-dev-smashed"</span>) | |
| <span class="hljs-comment"># 定义指标</span> | |
| metrics = [ | |
| TotalTimeMetric(n_iterations=<span class="hljs-number">20</span>, n_warmup_iterations=<span class="hljs-number">5</span>), | |
| ThroughputMetric(n_iterations=<span class="hljs-number">20</span>, n_warmup_iterations=<span class="hljs-number">5</span>), | |
| TorchMetricWrapper(<span class="hljs-string">"clip"</span>), | |
| ] | |
| <span class="hljs-comment"># 定义数据模块</span> | |
| datamodule = PrunaDataModule.from_string(<span class="hljs-string">"LAION256"</span>) | |
| datamodule.limit_datasets(<span class="hljs-number">10</span>) | |
| <span class="hljs-comment"># 定义任务和评估代理</span> | |
| task = Task(metrics, datamodule=datamodule, device=device) | |
| eval_agent = EvaluationAgent(task) | |
| <span class="hljs-comment"># 评估优化模型并卸载到CPU</span> | |
| smashed_pipe.move_to_device(device) | |
| smashed_pipe_results = eval_agent.evaluate(smashed_pipe) | |
| smashed_pipe.move_to_device(<span class="hljs-string">"cpu"</span>)<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-6gtl5s">现在您已经了解了如何优化和评估您的模型，可以开始使用 Pruna 来优化您自己的模型了。幸运的是，我们有许多示例来帮助您入门。</p> <blockquote class="tip" data-svelte-h="svelte-t41fkn"><p>有关基准测试 Flux 的更多详细信息，请查看 <a href="https://huggingface.co/blog/PrunaAI/flux-fastest-image-generation-endpoint" rel="nofollow">宣布 FLUX-Juiced：最快的图像生成端点（快 2.6 倍）！</a> 博客文章和 <a href="https://huggingface.co/spaces/PrunaAI/InferBench" rel="nofollow">InferBench</a> 空间。</p></blockquote> <h2 class="relative group"><a id="参考" 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="#参考"><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>参考</span></h2> <ul data-svelte-h="svelte-5ha4im"><li><a href="https://github.com/pruna-ai/pruna" rel="nofollow">Pruna</a></li> <li><a href="https://docs.pruna.ai/en/stable/docs_pruna/user_manual/configure.html#configure-algorithms" rel="nofollow">Pruna 优化</a></li> <li><a href="https://docs.pruna.ai/en/stable/docs_pruna/user_manual/evaluate.html" rel="nofollow">Pruna 评估</a></li> <li><a href="https://docs.pruna.ai/en/stable/docs_pruna/tutorials/index.html" rel="nofollow">Pruna 教程</a></li></ul> <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/pruna.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, 33], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 28.4 kB
- Xet hash:
- b187083066cad30aaaed797b9023439e10db2c6ce9933a00e0cd56c6f1e4f936
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.