Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Pruna","local":"pruna","sections":[{"title":"Installation","local":"installation","sections":[],"depth":2},{"title":"Optimize Diffusers models","local":"optimize-diffusers-models","sections":[],"depth":2},{"title":"Evaluate and benchmark Diffusers models","local":"evaluate-and-benchmark-diffusers-models","sections":[],"depth":2},{"title":"Reference","local":"reference","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/diffusers/pr_12249/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/entry/start.d78ccb7e.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/scheduler.53228c21.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/singletons.7109d99c.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/index.e93d0901.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/paths.85ae17be.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/entry/app.cd68c46f.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/preload-helper.20fd9bc3.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/index.100fac89.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/nodes/0.78828106.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/nodes/288.42a6b1fc.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/CopyLLMTxtMenu.133e28e0.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/globals.7f7f1b26.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/IconCopy.38cf8f56.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.d8195636.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/CodeBlock.d30a6509.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12249/en/_app/immutable/chunks/HfOption.fad27e59.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Pruna","local":"pruna","sections":[{"title":"Installation","local":"installation","sections":[],"depth":2},{"title":"Optimize Diffusers models","local":"optimize-diffusers-models","sections":[],"depth":2},{"title":"Evaluate and benchmark Diffusers models","local":"evaluate-and-benchmark-diffusers-models","sections":[],"depth":2},{"title":"Reference","local":"reference","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-doimg4"><a href="https://github.com/PrunaAI/pruna" rel="nofollow">Pruna</a> is a model optimization framework that offers various optimization methods - quantization, pruning, caching, compilation - for accelerating inference and reducing memory usage. A general overview of the optimization methods are shown below.</p> <table data-svelte-h="svelte-ct3fez"><thead><tr><th>Technique</th> <th>Description</th> <th align="center">Speed</th> <th align="center">Memory</th> <th align="center">Quality</th></tr></thead> <tbody><tr><td><code>batcher</code></td> <td>Groups multiple inputs together to be processed simultaneously, improving computational efficiency and reducing processing time.</td> <td align="center">✅</td> <td align="center">❌</td> <td align="center">➖</td></tr> <tr><td><code>cacher</code></td> <td>Stores intermediate results of computations to speed up subsequent operations.</td> <td align="center">✅</td> <td align="center">➖</td> <td align="center">➖</td></tr> <tr><td><code>compiler</code></td> <td>Optimises the model with instructions for specific hardware.</td> <td align="center">✅</td> <td align="center">➖</td> <td align="center">➖</td></tr> <tr><td><code>distiller</code></td> <td>Trains a smaller, simpler model to mimic a larger, more complex model.</td> <td align="center">✅</td> <td align="center">✅</td> <td align="center">❌</td></tr> <tr><td><code>quantizer</code></td> <td>Reduces the precision of weights and activations, lowering memory requirements.</td> <td align="center">✅</td> <td align="center">✅</td> <td align="center">❌</td></tr> <tr><td><code>pruner</code></td> <td>Removes less important or redundant connections and neurons, resulting in a sparser, more efficient network.</td> <td align="center">✅</td> <td align="center">✅</td> <td align="center">❌</td></tr> <tr><td><code>recoverer</code></td> <td>Restores the performance of a model after compression.</td> <td align="center">➖</td> <td align="center">➖</td> <td align="center">✅</td></tr> <tr><td><code>factorizer</code></td> <td>Factorization batches several small matrix multiplications into one large fused operation.</td> <td align="center">✅</td> <td align="center">➖</td> <td align="center">➖</td></tr> <tr><td><code>enhancer</code></td> <td>Enhances the model output by applying post-processing algorithms such as denoising or upscaling.</td> <td align="center">❌</td> <td align="center">-</td> <td align="center">✅</td></tr></tbody></table> <p data-svelte-h="svelte-vkdhl3">✅ (improves), ➖ (approx. the same), ❌ (worsens)</p> <p data-svelte-h="svelte-gicf0n">Explore the full range of optimization methods in the <a href="https://docs.pruna.ai/en/stable/docs_pruna/user_manual/configure.html#configure-algorithms" rel="nofollow">Pruna documentation</a>.</p> <h2 class="relative group"><a id="installation" 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="#installation"><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>Installation</span></h2> <p data-svelte-h="svelte-1mhda9e">Install Pruna with the following command.</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="optimize-diffusers-models" 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="#optimize-diffusers-models"><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>Optimize Diffusers models</span></h2> <p data-svelte-h="svelte-19uf75c">A broad range of optimization algorithms are supported for Diffusers models as shown below.</p> <div class="flex justify-center" data-svelte-h="svelte-1diaiat"><img src="https://huggingface.co/datasets/PrunaAI/documentation-images/resolve/main/diffusers/diffusers_combinations.png" alt="Overview of the supported optimization algorithms for diffusers models"></div> <p data-svelte-h="svelte-2q15d4">The example below optimizes <a href="https://huggingface.co/black-forest-labs/FLUX.1-dev" rel="nofollow">black-forest-labs/FLUX.1-dev</a> | |
| with a combination of factorizer, compiler, and cacher algorithms. This combination accelerates inference by up to 4.2x and cuts peak GPU memory usage from 34.7GB to 28.0GB, all while maintaining virtually the same output quality.</p> <blockquote class="tip" data-svelte-h="svelte-yl1m4o"><p>Refer to the <a href="https://docs.pruna.ai/en/stable/docs_pruna/user_manual/configure.html" rel="nofollow">Pruna optimization</a> docs to learn more about the optimization techniques used in this example.</p></blockquote> <div class="flex justify-center" data-svelte-h="svelte-4p98l1"><img src="https://huggingface.co/datasets/PrunaAI/documentation-images/resolve/main/diffusers/flux_combination.png" alt="Optimization techniques used for FLUX.1-dev showing the combination of factorizer, compiler, and cacher algorithms"></div> <p data-svelte-h="svelte-9w0h81">Start by defining a <code>SmashConfig</code> with the optimization algorithms to use. To optimize the model, wrap the pipeline and the <code>SmashConfig</code> with <code>smash</code> and then use the pipeline as normal for inference.</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"># load the model</span> | |
| <span class="hljs-comment"># Try segmind/Segmind-Vega or black-forest-labs/FLUX.1-schnell with a small GPU memory</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"># define the configuration</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"># for the best results in terms of speed you can add these configs</span> | |
| <span class="hljs-comment"># however they will increase your warmup time from 1.5 min to 10 min</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"># optimize the model</span> | |
| smashed_pipe = smash(pipe, smash_config) | |
| <span class="hljs-comment"># run the model</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-i3s1re">After optimization, we can share and load the optimized model using the Hugging Face Hub.</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"># save the model</span> | |
| smashed_pipe.save_to_hub(<span class="hljs-string">"<username>/FLUX.1-dev-smashed"</span>) | |
| <span class="hljs-comment"># load the model</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="evaluate-and-benchmark-diffusers-models" 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="#evaluate-and-benchmark-diffusers-models"><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>Evaluate and benchmark Diffusers models</span></h2> <p data-svelte-h="svelte-ocu867">Pruna provides the <a href="https://docs.pruna.ai/en/stable/docs_pruna/user_manual/evaluate.html" rel="nofollow">EvaluationAgent</a> to evaluate the quality of your optimized models.</p> <p data-svelte-h="svelte-sdkumj">We can metrics we care about, such as total time and throughput, and the dataset to evaluate on. We can define a model and pass it to the <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-1yv4f30">We can load and evaluate an optimized model by using the <code>EvaluationAgent</code> and pass it to the <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"># load the model</span> | |
| <span class="hljs-comment"># Try PrunaAI/Segmind-Vega-smashed or PrunaAI/FLUX.1-dev-smashed with a small GPU memory</span> | |
| smashed_pipe = PrunaModel.from_hub(<span class="hljs-string">"PrunaAI/FLUX.1-dev-smashed"</span>) | |
| <span class="hljs-comment"># Define the metrics</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"># Define the datamodule</span> | |
| datamodule = PrunaDataModule.from_string(<span class="hljs-string">"LAION256"</span>) | |
| datamodule.limit_datasets(<span class="hljs-number">10</span>) | |
| <span class="hljs-comment"># Define the task and evaluation agent</span> | |
| task = Task(metrics, datamodule=datamodule, device=device) | |
| eval_agent = EvaluationAgent(task) | |
| <span class="hljs-comment"># Evaluate smashed model and offload it to 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-10l7kab">Now that you have seen how to optimize and evaluate your models, you can start using Pruna to optimize your own models. Luckily, we have many examples to help you get started.</p> <blockquote class="tip" data-svelte-h="svelte-pwj0k3"><p>For more details about benchmarking Flux, check out the <a href="https://huggingface.co/blog/PrunaAI/flux-fastest-image-generation-endpoint" rel="nofollow">Announcing FLUX-Juiced: The Fastest Image Generation Endpoint (2.6 times faster)!</a> blog post and the <a href="https://huggingface.co/spaces/PrunaAI/InferBench" rel="nofollow">InferBench</a> Space.</p></blockquote> <h2 class="relative group"><a id="reference" 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="#reference"><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>Reference</span></h2> <ul data-svelte-h="svelte-e63z7a"><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 optimization</a></li> <li><a href="https://docs.pruna.ai/en/stable/docs_pruna/user_manual/evaluate.html" rel="nofollow">Pruna evaluation</a></li> <li><a href="https://docs.pruna.ai/en/stable/docs_pruna/tutorials/index.html" rel="nofollow">Pruna tutorials</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/en/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_15arw4w = { | |
| assets: "/docs/diffusers/pr_12249/en", | |
| base: "/docs/diffusers/pr_12249/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/diffusers/pr_12249/en/_app/immutable/entry/start.d78ccb7e.js"), | |
| import("/docs/diffusers/pr_12249/en/_app/immutable/entry/app.cd68c46f.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 288], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 29.4 kB
- Xet hash:
- ac8b6aab52cf5f58493307db563cb169f9574844b8f2d98b0319aeeba25c0563
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.