Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"ExecuTorch","local":"executorch","sections":[{"title":"Transformers integration","local":"transformers-integration","sections":[],"depth":2},{"title":"Resources","local":"resources","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/transformers/pr_39895/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/entry/start.ed44d8d9.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/scheduler.31fdf58d.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/singletons.6a6316d3.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/index.252883d5.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/paths.6325da18.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/entry/app.75a9946c.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/preload-helper.f369a5fb.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/index.2f76fdf0.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/nodes/0.4d11f797.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/nodes/22.2d4ad083.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/CopyLLMTxtMenu.121ef535.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.92a7ab29.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/IconCopy.ac192424.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/CodeBlock.e52df5d6.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_39895/en/_app/immutable/chunks/HfOption.fb051768.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"ExecuTorch","local":"executorch","sections":[{"title":"Transformers integration","local":"transformers-integration","sections":[],"depth":2},{"title":"Resources","local":"resources","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="executorch" 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="#executorch"><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>ExecuTorch</span></h1> <p data-svelte-h="svelte-1e9odct"><a href="https://docs.pytorch.org/executorch/stable/index.html" rel="nofollow">ExecuTorch</a> is a lightweight runtime for model inference on edge devices. It exports a PyTorch model into a portable, ahead-of-time format. A small C++ runtime plans memory and dispatches operations to hardware-specific backends. Execution and memory behavior is known before the model runs on device, so inference overhead is low.</p> <p data-svelte-h="svelte-tob6sw">Export a Transformers model with the <a href="https://huggingface.co/docs/optimum-executorch/en/index" rel="nofollow">optimum-executorch</a> library.</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">CLI </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">Python </div></div> <div class="language-select"><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="language-bash "><!-- HTML_TAG_START -->optimum-cli <span class="hljs-built_in">export</span> executorch \ | |
| --model <span class="hljs-string">"HuggingFaceTB/SmolLM2-135M-Instruct"</span> \ | |
| --task <span class="hljs-string">"text-generation"</span> \ | |
| --recipe <span class="hljs-string">"xnnpack"</span> \ | |
| --output_dir=<span class="hljs-string">"./smollm2_exported"</span><!-- HTML_TAG_END --></pre></div> </div> <h2 class="relative group"><a id="transformers-integration" 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="#transformers-integration"><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>Transformers integration</span></h2> <p data-svelte-h="svelte-x9ys1s">The export process uses several Transformers components.</p> <ol data-svelte-h="svelte-1e88bqx"><li><a href="/docs/transformers/pr_39895/en/main_classes/model#transformers.PreTrainedModel.from_pretrained">from_pretrained()</a> loads the model weights in safetensors format.</li> <li>Optimum applies graph optimizations and runs <a href="https://docs.pytorch.org/docs/stable/export.html" rel="nofollow">torch.export</a> to create a <code>model.pte</code> file targeting your hardware backend.</li> <li><a href="/docs/transformers/pr_39895/en/model_doc/auto#transformers.AutoTokenizer">AutoTokenizer</a> or <a href="/docs/transformers/pr_39895/en/model_doc/auto#transformers.AutoProcessor">AutoProcessor</a> loads the tokenizer or processor files and runs during inference.</li> <li>At runtime, a C++ runner class executes the <code>.pte</code> file on the ExecuTorch runtime.</li></ol> <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 class="hljs-keyword">include</span> <span class="hljs-string"><executorch/extension/llm/runner/text_llm_runner.h></span></span> | |
| <span class="hljs-keyword">using</span> <span class="hljs-keyword">namespace</span> executorch::extension::llm; | |
| <span class="hljs-function"><span class="hljs-type">int</span> <span class="hljs-title">main</span><span class="hljs-params">()</span> </span>{ | |
| <span class="hljs-comment">// Load tokenizer and create runner</span> | |
| <span class="hljs-keyword">auto</span> tokenizer = <span class="hljs-built_in">load_tokenizer</span>(<span class="hljs-string">"path/to/tokenizer.json"</span>, <span class="hljs-literal">nullptr</span>, std::<span class="hljs-literal">nullopt</span>, <span class="hljs-number">0</span>, <span class="hljs-number">0</span>); | |
| <span class="hljs-keyword">auto</span> runner = <span class="hljs-built_in">create_text_llm_runner</span>(<span class="hljs-string">"path/to/model.pte"</span>, std::<span class="hljs-built_in">move</span>(tokenizer)); | |
| <span class="hljs-comment">// Load the model</span> | |
| runner-><span class="hljs-built_in">load</span>(); | |
| <span class="hljs-comment">// Configure generation</span> | |
| GenerationConfig config; | |
| config.max_new_tokens = <span class="hljs-number">100</span>; | |
| config.temperature = <span class="hljs-number">0.8f</span>; | |
| <span class="hljs-comment">// Generate text with streaming output</span> | |
| runner-><span class="hljs-built_in">generate</span>(<span class="hljs-string">"The capital of France is"</span>, config, | |
| [](<span class="hljs-type">const</span> std::string& token) { std::cout << token << std::flush; }, | |
| <span class="hljs-literal">nullptr</span>); | |
| <span class="hljs-keyword">return</span> <span class="hljs-number">0</span>; | |
| }<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="resources" 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="#resources"><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>Resources</span></h2> <ul data-svelte-h="svelte-h1dkkz"><li><a href="https://docs.pytorch.org/executorch/stable/index.html" rel="nofollow">ExecuTorch</a> docs</li> <li><a href="https://docs.pytorch.org/docs/stable/export.html" rel="nofollow">torch.export</a> docs</li> <li><a href="../serialization#executorch">Exporting to production</a> guide</li></ul> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/en/community_integrations/executorch.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_sw4oup = { | |
| assets: "/docs/transformers/pr_39895/en", | |
| base: "/docs/transformers/pr_39895/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/transformers/pr_39895/en/_app/immutable/entry/start.ed44d8d9.js"), | |
| import("/docs/transformers/pr_39895/en/_app/immutable/entry/app.75a9946c.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 22], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 16.4 kB
- Xet hash:
- bd96a8f94511bf464f897955618de68d88fa150fd5482bc413f7db9c45e8befa
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.