Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / transformers /pr_36895 /en /torch_compile.html

HuggingFaceDocBuilder

2 months ago

download

raw

14 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"torch.compile","local":"torchcompile","sections":[{"title":"Backend","local":"backend","sections":[],"depth":2},{"title":"Compile mode","local":"compile-mode","sections":[],"depth":2},{"title":"Next steps","local":"next-steps","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/transformers/pr_36895/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/entry/start.b88698fb.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/chunks/scheduler.31fdf58d.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/chunks/singletons.18caffe4.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/chunks/index.252883d5.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/chunks/paths.a82d371a.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/entry/app.ac300a2c.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/chunks/preload-helper.643b8c40.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/chunks/index.2f76fdf0.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/nodes/0.1669b2ea.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/nodes/679.8e29425b.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/chunks/CopyLLMTxtMenu.9cbc081e.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.945f6700.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/chunks/IconCopy.ac192424.js">
	<link rel="modulepreload" href="/docs/transformers/pr_36895/en/_app/immutable/chunks/CodeBlock.e52df5d6.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"torch.compile","local":"torchcompile","sections":[{"title":"Backend","local":"backend","sections":[],"depth":2},{"title":"Compile mode","local":"compile-mode","sections":[],"depth":2},{"title":"Next steps","local":"next-steps","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="torchcompile" 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="#torchcompile"><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>torch.compile</span></h1> <p data-svelte-h="svelte-3f46hv"><a href="https://docs.pytorch.org/tutorials/intermediate/torch_compile_tutorial.html" rel="nofollow">torch.compile</a> compiles PyTorch code to fused kernels to make it run faster. For training, it traces both the forward and backward pass together and compiles them into optimized kernels, reducing the overhead of individual op launches and fusing operations to cut memory bandwidth usage.</p> <p data-svelte-h="svelte-mlmqbb">Set <code>torch_compile=True</code> in <a href="/docs/transformers/pr_36895/en/main_classes/trainer#transformers.TrainingArguments">TrainingArguments</a> to enable it. Training compiles both the forward and backward pass, unlike inference which only compiles the forward pass. Compilation happens on the first training step, so expect it to be significantly slower than subsequent steps.</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="language-py "><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> TrainingArguments

	args = TrainingArguments(
	...,
	torch_compile=<span class="hljs-literal">True</span>,
	torch_compile_backend=<span class="hljs-string">"inductor"</span>,
	torch_compile_mode=<span class="hljs-string">"reduce-overhead"</span>,
	)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="backend" 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="#backend"><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>Backend</span></h2> <p data-svelte-h="svelte-ykouwf">The default backend is <code>inductor</code>, which compiles to Triton kernels with AOTAutograd. This is the right choice for most training workloads. Use <code>cudagraphs</code> for fixed-shape inputs, or <code>ipex</code> for Intel CPU training.</p> <h2 class="relative group"><a id="compile-mode" 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="#compile-mode"><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>Compile mode</span></h2> <p data-svelte-h="svelte-vch9nb">Use the table below to help select a <code>torch.compile</code> mode.</p> <table data-svelte-h="svelte-1dzvdbx"><thead><tr><th>mode</th> <th>description</th></tr></thead> <tbody><tr><td>default</td> <td>balanced compile time vs runtime</td></tr> <tr><td>reduce-overhead</td> <td>reduces Python/CPU overhead using CUDA graphs at the cost of some extra memory</td></tr> <tr><td>max-autotune</td> <td>benchmarks multiple kernel implementations at compile and picks the fastest (longer compilation)</td></tr> <tr><td>max-autotune-no-cudagraphs</td> <td>same as max-autotune but without CUDA graphs</td></tr></tbody></table> <h2 class="relative group"><a id="next-steps" 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="#next-steps"><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>Next steps</span></h2> <ul data-svelte-h="svelte-78hsni"><li>See the <a href="./perf_torch_compile">torch.compile for inference</a> guide for details on fullgraph compilation and inference benchmarks.</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/torch_compile.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_1s77840 = {
	assets: "/docs/transformers/pr_36895/en",
	base: "/docs/transformers/pr_36895/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/transformers/pr_36895/en/_app/immutable/entry/start.b88698fb.js"),
	import("/docs/transformers/pr_36895/en/_app/immutable/entry/app.ac300a2c.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 679],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 14 kB
Xet hash:: fa61cf75fae64c208e28394db4ecb1be19d3e3952551cd58cf9d24efb8d26a3b

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