Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / transformers /pr_26617 /en /kernel_doc /overview.html

rtrm

about 1 month ago

download

raw

12 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Kernels","local":"kernels","sections":[{"title":"Determinism","local":"determinism","sections":[],"depth":2},{"title":"Resources","local":"resources","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/transformers/pr_26617/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/entry/start.b5ae2c21.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/chunks/scheduler.31fdf58d.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/chunks/singletons.512cdb48.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/chunks/index.252883d5.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/chunks/paths.81255c3b.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/entry/app.9acf2c3e.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/chunks/preload-helper.bb442aeb.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/chunks/index.2f76fdf0.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/nodes/0.da6b3909.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/nodes/65.9947387f.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/chunks/CopyLLMTxtMenu.a69e059a.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.e4c7f916.js">
	<link rel="modulepreload" href="/docs/transformers/pr_26617/en/_app/immutable/chunks/IconCopy.ac192424.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Kernels","local":"kernels","sections":[{"title":"Determinism","local":"determinism","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="kernels" 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="#kernels"><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>Kernels</span></h1> <p data-svelte-h="svelte-1flfpn5">PyTorch operations are general-purpose. Hardware vendors and the community create specialized implementations that run faster on specific platforms. Installing these optimized kernels is a challenge because it requires matching compiler versions, CUDA toolkits, and platform-specific builds.</p> <table data-svelte-h="svelte-j7hm59"><thead><tr><th align="left">platform</th> <th align="left">supported devices</th></tr></thead> <tbody><tr><td align="left">NVIDIA GPUs (CUDA)</td> <td align="left">Modern architectures with compute capability 7.0+ (Volta, Turing, Ampere, Hopper, Blackwell)</td></tr> <tr><td align="left">AMD GPUs (ROCm)</td> <td align="left">Compatible with ROCm-supported devices</td></tr> <tr><td align="left">Apple Silicon (Metal)</td> <td align="left">M-series chips (M1, M2, M3, M4 and newer)</td></tr> <tr><td align="left">Intel GPUs (XPU)</td> <td align="left">Intel Data Center GPU Max Series and compatible devices</td></tr></tbody></table> <p data-svelte-h="svelte-a9y3s1"><a href="https://huggingface.co/docs/kernels/index" rel="nofollow">Kernels</a> solves this by distributing precompiled binaries through the <a href="https://huggingface.co/kernels-community" rel="nofollow">Hub</a>. It detects your platform at runtime and loads the right binary automatically.</p> <p data-svelte-h="svelte-1xoygap">When <code>use_kernels=True</code>, Transformers identifies layers with available optimized kernel implementations. It downloads and <a href="../installation#cache-directory">caches</a> kernels from the Hub only when needed to reduce startup time. Kernels accelerate compute-intensive operations such as attention, normalization, and fused operations.</p> <p data-svelte-h="svelte-1rp62gd">Not all operations have kernel implementations. The library falls back to standard PyTorch when no kernel is available.</p> <h2 class="relative group"><a id="determinism" 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="#determinism"><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>Determinism</span></h2> <p data-svelte-h="svelte-jdypu">Some kernels produce slightly different results than PyTorch due to operation reordering or accumulation strategies. These differences are functionally equivalent but affect reproducibility.</p> <p data-svelte-h="svelte-18nz6ow">For deterministic behavior, try the following.</p> <ul data-svelte-h="svelte-15x7yie"><li>Check kernel repository documentation for determinism guarantees. For example, the SDPA kernel in <a href="https://huggingface.co/kernels-community/gpt-oss-metal-kernels#4-scaled-dot-product-attention-sdpa" rel="nofollow">gpt-oss-metal-kernels</a> matches the PyTorch implementation 97% of the time.</li> <li>Disable specific kernels that affect your use case.</li> <li>Set random seeds and PyTorch deterministic flags.</li></ul> <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-17auedm"><li><a href="./loading_kernels">Loading kernels</a> guide to get started</li> <li><a href="https://github.com/huggingface/kernels" rel="nofollow">Kernels</a> GitHub repository</li> <li><a href="https://huggingface.co/blog/hello-hf-kernels" rel="nofollow">Enhance Your Models in 5 Minutes with the Hugging Face Kernel Hub</a> blog post</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/kernel_doc/overview.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_1x0t0ja = {
	assets: "/docs/transformers/pr_26617/en",
	base: "/docs/transformers/pr_26617/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/transformers/pr_26617/en/_app/immutable/entry/start.b5ae2c21.js"),
	import("/docs/transformers/pr_26617/en/_app/immutable/entry/app.9acf2c3e.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 65],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 12 kB
Xet hash:: d84801095d109d291e26737da269e72f9f862f23c27c52affeebcbe376b615cf

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