google-cloud/pr_113/en/examples/cloud-run-index.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;(Preview) Cloud Run Examples&quot;,&quot;local&quot;:&quot;preview-cloud-run-examples&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Inference Examples&quot;,&quot;local&quot;:&quot;inference-examples&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Training Examples&quot;,&quot;local&quot;:&quot;training-examples&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/google-cloud/pr_113/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/google-cloud/pr_113/en/_app/immutable/entry/start.3fa28be1.js">
		<link rel="modulepreload" href="/docs/google-cloud/pr_113/en/_app/immutable/chunks/scheduler.b108d059.js">
		<link rel="modulepreload" href="/docs/google-cloud/pr_113/en/_app/immutable/chunks/singletons.e5e8fb57.js">
		<link rel="modulepreload" href="/docs/google-cloud/pr_113/en/_app/immutable/chunks/paths.0d296fb5.js">
		<link rel="modulepreload" href="/docs/google-cloud/pr_113/en/_app/immutable/entry/app.8572c6c6.js">
		<link rel="modulepreload" href="/docs/google-cloud/pr_113/en/_app/immutable/chunks/index.008de539.js">
		<link rel="modulepreload" href="/docs/google-cloud/pr_113/en/_app/immutable/nodes/0.d1a2de3e.js">
		<link rel="modulepreload" href="/docs/google-cloud/pr_113/en/_app/immutable/nodes/6.c9c46518.js">
		<link rel="modulepreload" href="/docs/google-cloud/pr_113/en/_app/immutable/chunks/Tip.aeb15ab7.js">
		<link rel="modulepreload" href="/docs/google-cloud/pr_113/en/_app/immutable/chunks/EditOnGithub.d1c48e3d.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;(Preview) Cloud Run Examples&quot;,&quot;local&quot;:&quot;preview-cloud-run-examples&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Inference Examples&quot;,&quot;local&quot;:&quot;inference-examples&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Training Examples&quot;,&quot;local&quot;:&quot;training-examples&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="preview-cloud-run-examples" 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="#preview-cloud-run-examples"><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>(Preview) Cloud Run Examples</span></h1> <p data-svelte-h="svelte-ezsq2o">This directory contains usage examples of the Hugging Face Deep Learning Containers (DLCs) in Cloud Run only for inference at the moment, with a focus on Large Language Models (LLMs).</p>  <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"><p data-svelte-h="svelte-1b11u3p">Cloud Run now offers on-demand access to NVIDIA L4 GPUs for running AI inference workloads; but is still in preview, so the Cloud Run examples within this repository should be taken solely for testing and experimentation; please avoid using those for production workloads. We are actively working towards general availability and appreciate your understanding.</p></div>  <h2 class="relative group"><a id="inference-examples" 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="#inference-examples"><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>Inference Examples</span></h2> <table data-svelte-h="svelte-vg0xte"><thead><tr><th>Example</th> <th>Title</th></tr></thead> <tbody><tr><td><a href="https://github.com/huggingface/Google-Cloud-Containers/tree/main/examples/cloud-run/deploy-gemma-2-on-cloud-run" rel="nofollow">deploy-gemma-2-on-cloud-run</a></td> <td>Deploy Gemma2 9B with TGI DLC on Cloud Run</td></tr> <tr><td><a href="https://github.com/huggingface/Google-Cloud-Containers/tree/main/examples/cloud-run/deploy-llama-3-1-on-cloud-run" rel="nofollow">deploy-llama-3-1-on-cloud-run</a></td> <td>Deploy Llama 3.1 8B with TGI DLC on Cloud Run</td></tr></tbody></table>  <h2 class="relative group"><a id="training-examples" 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="#training-examples"><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>Training Examples</span></h2> <p data-svelte-h="svelte-15n2n4z">Coming soon!</p> <hr>  <div class="course-tip  bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-1g7fiyb">📍 Find the complete example on GitHub <a href="https://github.com/huggingface/Google-Cloud-Containers/tree/main/examples/cloud-run" rel="nofollow">here</a>!</p></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/Google-Cloud-Containers/blob/main/docs/source/examples/cloud-run-index.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_1alknr2 = {
						assets: "/docs/google-cloud/pr_113/en",
						base: "/docs/google-cloud/pr_113/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/google-cloud/pr_113/en/_app/immutable/entry/start.3fa28be1.js"),
						import("/docs/google-cloud/pr_113/en/_app/immutable/entry/app.8572c6c6.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 6],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>