text-generation-inference/pr_2965/en/multi_backend_support.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Multi-backend support&quot;,&quot;local&quot;:&quot;multi-backend-support&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/text-generation-inference/pr_2965/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/text-generation-inference/pr_2965/en/_app/immutable/entry/start.6569fc45.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/pr_2965/en/_app/immutable/chunks/scheduler.362310b7.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/pr_2965/en/_app/immutable/chunks/singletons.189677f5.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/pr_2965/en/_app/immutable/chunks/index.7f53ec41.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/pr_2965/en/_app/immutable/chunks/paths.323159e8.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/pr_2965/en/_app/immutable/entry/app.98c60904.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/pr_2965/en/_app/immutable/chunks/index.57dfc70d.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/pr_2965/en/_app/immutable/nodes/0.69e98ac5.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/pr_2965/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/pr_2965/en/_app/immutable/nodes/33.0f51f8e9.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/pr_2965/en/_app/immutable/chunks/EditOnGithub.9633c464.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Multi-backend support&quot;,&quot;local&quot;:&quot;multi-backend-support&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="multi-backend-support" 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="#multi-backend-support"><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>Multi-backend support</span></h1> <p data-svelte-h="svelte-130turw">TGI (Text Generation Inference) offers flexibility by supporting multiple backends for serving large language models (LLMs).
With multi-backend support, you can choose the backend that best suits your needs,
whether you prioritize performance, ease of use, or compatibility with specific hardware. API interaction with
TGI remains consistent across backends, allowing you to switch between them seamlessly.</p> <p data-svelte-h="svelte-1164h5e"><strong>Supported backends:</strong></p> <ul data-svelte-h="svelte-1x8xqdm"><li><strong>TGI CUDA backend</strong>: This high-performance backend is optimized for NVIDIA GPUs and serves as the default option
within TGI. Developed in-house, it boasts numerous optimizations and is used in production by various projects, including those by Hugging Face.</li> <li><strong><a href="./backends/trtllm">TGI TRTLLM backend</a></strong>: This backend leverages NVIDIA’s TensorRT library to accelerate LLM inference.
It utilizes specialized optimizations and custom kernels for enhanced performance.
However, it requires a model-specific compilation step for each GPU architecture.</li></ul> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/text-generation-inference/blob/main/docs/source/multi_backend_support.md" 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_1q4976k = {
						assets: "/docs/text-generation-inference/pr_2965/en",
						base: "/docs/text-generation-inference/pr_2965/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/text-generation-inference/pr_2965/en/_app/immutable/entry/start.6569fc45.js"),
						import("/docs/text-generation-inference/pr_2965/en/_app/immutable/entry/app.98c60904.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 33],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>