text-generation-inference/main/en/index.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Text Generation Inference&quot;,&quot;local&quot;:&quot;text-generation-inference&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/text-generation-inference/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/entry/start.1810066f.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/scheduler.362310b7.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/singletons.fa2b0eb7.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/index.7f53ec41.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/paths.284aef40.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/entry/app.8cfc1931.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/index.57dfc70d.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/nodes/0.543c9bd9.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/nodes/23.18c9be67.js">
		<link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/EditOnGithub.9633c464.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Text Generation Inference&quot;,&quot;local&quot;:&quot;text-generation-inference&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="text-generation-inference" 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="#text-generation-inference"><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>Text Generation Inference</span></h1> <p data-svelte-h="svelte-m7gv0">Text Generation Inference (TGI) is a toolkit for deploying and serving Large Language Models (LLMs). TGI enables high-performance text generation for the most popular open-source LLMs, including Llama, Falcon, StarCoder, BLOOM, GPT-NeoX, and T5.</p> <p data-svelte-h="svelte-1rntzol"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/TGI.png" alt="Text Generation Inference"></p> <p data-svelte-h="svelte-u1ae6o">Text Generation Inference implements many optimizations and features, such as:</p> <ul data-svelte-h="svelte-1brewrd"><li>Simple launcher to serve most popular LLMs</li> <li>Production ready (distributed tracing with Open Telemetry, Prometheus metrics)</li> <li>Tensor Parallelism for faster inference on multiple GPUs</li> <li>Token streaming using Server-Sent Events (SSE)</li> <li>Continuous batching of incoming requests for increased total throughput</li> <li>Optimized transformers code for inference using <a href="https://github.com/HazyResearch/flash-attention" rel="nofollow">Flash Attention</a> and <a href="https://github.com/vllm-project/vllm" rel="nofollow">Paged Attention</a> on the most popular architectures</li> <li>Quantization with <a href="https://github.com/TimDettmers/bitsandbytes" rel="nofollow">bitsandbytes</a> and <a href="https://arxiv.org/abs/2210.17323" rel="nofollow">GPT-Q</a></li> <li><a href="https://github.com/huggingface/safetensors" rel="nofollow">Safetensors</a> weight loading</li> <li>Watermarking with <a href="https://arxiv.org/abs/2301.10226" rel="nofollow">A Watermark for Large Language Models</a></li> <li>Logits warper (temperature scaling, top-p, top-k, repetition penalty)</li> <li>Stop sequences</li> <li>Log probabilities</li> <li>Fine-tuning Support: Utilize fine-tuned models for specific tasks to achieve higher accuracy and performance.</li> <li><a href="../conceptual/guidance">Guidance</a>: Enable function calling and tool-use by forcing the model to generate structured outputs based on your own predefined output schemas.</li></ul> <p data-svelte-h="svelte-uziyu5">Text Generation Inference is used in production by multiple projects, such as:</p> <ul data-svelte-h="svelte-stiskr"><li><a href="https://github.com/huggingface/chat-ui" rel="nofollow">Hugging Chat</a>, an open-source interface for open-access models, such as Open Assistant and Llama</li> <li><a href="https://open-assistant.io/" rel="nofollow">OpenAssistant</a>, an open-source community effort to train LLMs in the open</li> <li><a href="http://nat.dev/" rel="nofollow">nat.dev</a>, a playground to explore and compare LLMs.</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/index.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_1dfb6m4 = {
						assets: "/docs/text-generation-inference/main/en",
						base: "/docs/text-generation-inference/main/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/text-generation-inference/main/en/_app/immutable/entry/start.1810066f.js"),
						import("/docs/text-generation-inference/main/en/_app/immutable/entry/app.8cfc1931.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 23],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>