CINXE.COM

<!DOCTYPE html> <html lang='en' class='h-100'> <head> <meta name="viewport" content="width=device-width,initial-scale=1"> <meta name="csrf-param" content="authenticity_token" /> <meta name="csrf-token" content="qKUi3iiwTJByWLqXtyEQo_DPjX1reWtN6yRbl1-gtrOBRMP6mN6Ch68EUT6Hf6-3DD1yVNXjx5H6vfpCcG5W-A" /> <meta name="csp-nonce" /> <title>NeMo Microservices Early Access | NVIDIA Developer</title> <meta name="description" content="Apply now to easily and rapidly build and deploy large language model (LLM) workloads."> <meta name="keywords" content="nemo, llm, nemo microservices, nvidia"> <link rel="canonical" href="https://developer.nvidia.com/nemo-microservices"> <link rel="alternate" href="https://developer.nvidia.com/nemo-microservices" hreflang="x-default"> <link rel="alternate" href="https://developer.nvidia.com/nemo-microservices" hreflang="en-us"> <meta property="og:site_name" content="NVIDIA Developer"> <meta property="og:title" content="NeMo Microservices Early Access"> <meta property="og:description" content="Apply now to build and deploy large language model (LLM) workloads."> <meta property="og:type" content="website"> <meta property="og:image" content="https://developer.download.nvidia.com/images/og-default.jpg"> <meta property="og:url" content="https://developer.nvidia.com/nemo-microservices"> <meta name="twitter:title" content="NVIDIA NeMo Microservices Early Access"> <meta name="twitter:description" content="Apply today to build and deploy large language model (LLM) workloads easily and rapidly."> <meta name="twitter:image" content="https://developer.download.nvidia.com/images/og-default.jpg"> <meta name="twitter:site" content="@NVIDIA"> <meta name="twitter:card" content="summary_large_image"> <meta name="twitter:creator" content="@nvidiaaideveloper"> <meta property="interest" content="Conversational AI"> <link rel="stylesheet" href="https://dirms4qsy6412.cloudfront.net/assets/application-1e91adb0e814253f53c7a621169b6daa7cc975f97befa1c8f1a2ffe493719eb1.css" media="all" /> <link rel="stylesheet" href="https://dirms4qsy6412.cloudfront.net/assets/one-trust-bea625cf16a072ce5fdb0707a19f2645daf63c05eb1a016db72773eba008fc07.css" /> <script src="https://cdn.cookielaw.org/scripttemplates/otSDKStub.js" data-document-language="true" type="text/javascript" charset="UTF-8" data-domain-script="3e2b62ff-7ae7-4ac5-87c8-d5949ecafff5"></script> <script src="https://dirms4qsy6412.cloudfront.net/assets/onetrust-overrides-v2-9d7d1399c432d702a5bf32a31067737e10c123fdbe5ffef8ae83a34cf2d680ee.js"></script> <script> function OptanonWrapper() { let event = new Event('bannerLoaded'); window.dispatchEvent(event); if (window.OnetrustActiveGroups && window.OnetrustActiveGroups.includes("C0002")) { window.DD_RUM && window.DD_RUM.init({ clientToken: 'pub0430c74fae5d2b467bcb8d48b13e5b32', applicationId: '9fc963c7-14e6-403d-bdec-ee671550bb7f', site: 'datadoghq.com', service: 'devzone', env: 'production', version: '', sessionSampleRate: 10, sessionReplaySampleRate: 5, trackUserInteractions: true, trackResources: true, trackLongTasks: true, defaultPrivacyLevel: 'mask-user-input', }); } } </script> <script> (function() { var didInit = false; function initMunchkin() { if(didInit === false) { didInit = true; Munchkin.init('156-OFN-742'); } } var s = document.createElement('script'); s.type = 'text/javascript'; s.async = true; s.src = '//munchkin.marketo.net/munchkin.js'; s.onreadystatechange = function() { if (this.readyState == 'complete' || this.readyState == 'loaded') { initMunchkin(); } }; s.onload = initMunchkin; document.getElementsByTagName('head')[0].appendChild(s); })(); </script> <meta name='typesense-host' content='typesense.svc.nvidia.com'> <meta name='typesense-key' content='uFs9XGl9BWS7af7eAIbKNQ49sJnjEfQk'> <script src="https://developer.download.nvidia.com/scripts/typesense.js"></script> <script src="https://assets.adobedtm.com/5d4962a43b79/c1061d2c5e7b/launch-191c2462b890.min.js" data-ot-ignore="true"></script> <script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.6.3/jquery.min.js" integrity="sha512-STof4xm1wgkfm7heWqFJVn58Hm3EtS31XFaagaa8VMReCXAkQnJZ+jEy8PCC/iT18dFy95WcExNHFTqLyp72eQ==" crossorigin="anonymous" referrerpolicy="no-referrer"></script> <script src="https://dirms4qsy6412.cloudfront.net/assets/bootstrap/5.1.3/bootstrap.bundle.min-51ad1d8cab4ebd9873a0429f5e67ca717a71fd96daf8025bc04a88848e5b375c.js"></script> <link rel="icon" type="image/x-icon" href="https://dirms4qsy6412.cloudfront.net/assets/favicon-81bff16cada05fcff11e5711f7e6212bdc2e0a32ee57cd640a8cf66c87a6cbe6.ico" /> </head> <body class='d-flex flex-column h-100'> <div id='header'></div> <div id='page-mobile-nav-container'></div> <div class='page'> <div class="custom-html-wrapper"> <div class="custom-html-wrapper__code"><div id="join-nvd-banner" style="background:linear-gradient(rgb(153, 153, 153) 0%, rgb(102, 102, 102) 100%);padding:1em 0px;color:white;" class=""> <div class="container"> <div class="col-12 text-center"> New Llama 3.1 NIM inference microservices available.   <a target="blank" href="https://www.nvidia.com/en-us/ai" class="cta--prim m-0 ml-2">Get Started</a> </div> </div> </div></div> <div data-react-class="CustomHtml" data-react-props="{"preview":false}"></div> </div> <div class="container page"><section id="iwim"><h1 class="text-center h--large">Apply for Early Access to NVIDIA NeMo Microservices<br></h1><div class="separator separator--30"></div><p class="text-center lead">NVIDIA NeMo™ is an end-to-end platform for building and customizing enterprise-grade generative AI models that can be deployed anywhere, across cloud and data centers. NeMo microservices provide the easiest way to customize and evaluate generative AI models while supporting retrieval-augmented generation (RAG) in applications. Explore the microservices available in our early access program and apply below.<br></p><div class="separator separator--30"></div></section></div><section id="iuv7k" class="page__section--light-gray"><div class="container cntnr--cozy"><div class="separator separator--30"></div><h2 class="text-center h--medium">How to Apply<br></h2><p class="text-center">To request early access, follow these steps:<br></p><div class="row mt-4"><div class="col-12 col-md pb-4 pb-md-0"><img src="https://developer.download.nvidia.com/icons/ai-workbench/m48-developer.svg" alt="Placeholder" class="mb-3 mw-6-rem"><h3 id="i8b9r" class="h--smallest">Register for an Account<br></h3><p id="i7aig">Early access to NeMo microservices requires an <a href="/developer-program" id="in45ls">NVIDIA Developer Program</a> account, which also gives you access to exclusive learning resources to accelerate your generative AI development.<br></p></div><div class="col-12 col-md pb-4 pb-md-0"><img src="https://developer.download.nvidia.com/icons/m48-pencil-edit.svg" alt="Placeholder" class="mb-3 img-fluid mw-6-rem"><h3 id="igr0y" class="h--smallest">Apply for Early Access</h3><p id="irjsq">Fill out one of the request forms below to apply to your desired early access program.<br></p></div><div class="col-12 col-md pb-4 pb-md-0"><img src="https://developer.download.nvidia.com/icons/m48-check-mark-approved.svg" alt="Placeholder" class="mb-3 mw-6-rem"><h3 id="iekpe" class="h--smallest">Await Email Confirmation<br></h3><p id="i6i4x">If your request is approved, you'll receive a welcome email. Please make sure nvidia.com domains are added to your safe list to avoid emails being flagged as spam.<br></p></div><div class="col-12 col-md pb-4 pb-md-0"><img src="https://developer.download.nvidia.com/icons/m48-configuration-sdk.svg" alt="Placeholder" class="mb-3 mw-6-rem"><h3 id="iatgl" class="h--smallest">Access the Member’s Page <br></h3><p id="i8hua">A link will be included in your approval email. Follow this link to get to the members’ portal, resources, and NVIDIA NGC™, where you can access the microservices. <br></p></div></div></div></section><section id="ihklpx"><div class="container"><div class="separator separator--30"></div><div class="row cards__list"><div class="card-col col-lg-6"><div class="card-wrapper"><div class="card"><img alt="img-alt-text" src="https://developer.download.nvidia.com/images/products/generative-ai-development.jpg" class="img-fluid"><div class="card__content"><div class="card__text"></div><div class="card__cta"></div></div></div></div></div><div class="col-lg-6"><div id="iuxhsk"><div id="i997zc"><div id="i0qchj"><div id="io6z61"><div class="separator separator--30"></div><h3 class="txt-clr--blck mb-0 h--small">NVIDIA NeMo Microservices for Generative AI</h3><div class="separator separator--30"></div><p id="icova2">NeMo provides microservices that simplify the generative AI development and deployment process at scale, allowing organizations to connect LLMs to their enterprise data sources:<br></p><ul class="nv-list"><li id="ie72a3"><p class="mb-0">NVIDIA NeMo Curator enables high-quality dataset generation for LLM training.</p></li></ul><ul class="nv-list"><li><p class="mb-0">NVIDIA NeMo Customizer simplifies the fine-tuning and alignment of models while accelerating performance and scalability. <br></p></li></ul><ul class="nv-list"><li id="iv274"><p class="mb-0">NVIDIA NeMo Evaluator provides automatic assessment across various academic and custom benchmarks, delivering fast, easy, and reliable evaluation of custom large language models (LLMs) and RAGs.</p></li></ul><ul class="nv-list"><li id="ihlmw3"><p class="mb-0">NVIDIA NeMo Guardrails provides pre-packaged, API-accessible tooling for safeguarding LLM-powered applications</p></li><li id="i42hlm"><p class="mb-0">NVIDIA NeMo Retriever, a collection of generative AI microservices, enables organizations to seamlessly connect custom models to diverse business data and deliver highly accurate responses. The multimodal PDF data ingestion blueprint uses NeMo Retriever NIM microservices to provide high accuracy and throughput document processing.</p></li></ul><p id="i1u06l"><br>To participate, please fill out the short application and provide details about your use case. You must be a member of the <a href="/developer-program">NVIDIA Developer Program</a> and log in with your organization's email address. Applications from personal email accounts will be declined.<br><br>After approval, users will need to sign a non-disclosure agreement (NDA) to receive access.<br></p></div><div id="i1rndt"><a href="/nemo-microservices-early-access/join" class="link-cta text-transform-unset fw-bold">Apply to Access Now</a></div></div></div></div></div></div><hr class="separator separator--md"><div class="separator separator--30"></div><div class="row cards__list"><div class="card-col col-lg-6"><div class="card-wrapper"><div class="card"><img alt="img-alt-text" src="https://developer.download.nvidia.com/images/products/og-nvidia-nemo-1200x630.jpg" class="img-fluid"><div class="card__content"><div class="card__text"></div><div class="card__cta"></div></div></div></div></div><div class="col-lg-6"><div id="ikg3xj"><div id="ikygjl"><div id="i4zd11"><div id="ig6tpa"><div class="separator separator--30"></div><h3 class="txt-clr--blck mb-0 h--small">NVIDIA NeMo Service</h3><div class="separator separator--30"></div><p id="ierce4">The NVIDIA NeMo service allows for easy customization and deployment of LLMs for enterprise use cases. NeMo is currently in private, early access. This early access program provides:</p><ul class="nv-list"><li><p class="mb-0">A playground to use and experiment with LLMs, including instruct-tuned models for different business needs<br></p></li></ul><ul class="nv-list"><li id="isot9q"><p class="mb-0">The ability to customize a pretrained LLM using p-tuning techniques for a domain-specific use case or task </p></li></ul><ul class="nv-list"><li id="itr5x3"><p class="mb-0">The ability to deploy LLMs on premises or cloud, experiment via the playground, or use the service’s customization or inference APIs</p></li></ul></div><p id="iw3t7q">To participate, please fill out the short application and provide details about your use case. You must be a member of the <a href="/developer-program" id="i33ewh">NVIDIA Developer Program</a> and log in with your organization's email address. Applications from personal email accounts will be declined.<br><br>After approval, users will need to sign an NDA to receive access.<br></p><div id="imnevf"><a href="/nemo-llm-service-early-access/join" class="link-cta text-transform-unset fw-bold">Apply to Access Now</a></div></div></div></div></div></div></div></section> </div> <div id='footer' class='mt-auto'></div> <script type="text/javascript"> (() => { const handleQuotesBlock = (quotesBlock, idx) => { const blockquotes = quotesBlock.querySelectorAll('blockquote'); if (blockquotes.length < 1) { return; } const navContainer = document.createElement('ul'); navContainer.classList.add('quotes-list-navigation'); for (let i = 0; i < blockquotes.length; i++) { let navItem = document.createElement('li'); let btn = document.createElement('button'); btn.type = 'button'; btn.dataset['group'] = idx.toString(); btn.dataset['length'] = blockquotes.length.toString(); btn.value = i.toString(); btn.addEventListener('click', (e) => { const group = e.target.dataset['group']; const groupActiveButtons = document.querySelectorAll(`button[data-group="${group}"].active`); groupActiveButtons.forEach((activeButton) => { activeButton.classList.remove('active'); }); e.target.classList.add('active'); const viewPortWidth = quotesBlock.getBoundingClientRect().width; const clickedSlide = parseInt(e.target.value); quotesBlock.querySelector('.quotes-list').style.transform = `translate(-${viewPortWidth * clickedSlide}px)`; }); navItem.appendChild(btn); navContainer.appendChild(navItem); if (i === 0) { btn.click(); } } quotesBlock.appendChild(navContainer); }; const refreshQuotesBlock = () => { document.querySelectorAll('.quotes-list-navigation button.active').forEach((b) => { const currentItem = parseInt(b.value); const maxItem = parseInt(b.dataset['length']); const group = parseInt(b.dataset['group']); const next = currentItem + 1; if (next < maxItem) { document.querySelectorAll(`button[data-group="${group}"]`)[next].click(); } else { document.querySelectorAll(`button[data-group="${group}"]`)[0].click(); } }); }; const refreshInterval = 4000; const quotesBlocks = document.querySelectorAll('.quotes-list-viewport'); if (quotesBlocks.length) { quotesBlocks.forEach(handleQuotesBlock); setInterval(refreshQuotesBlock, refreshInterval); } })(); </script> <script type="text/javascript" charset="utf-8"> (() => { const doInit = (accordionRoot, idx) => { const baseID = `page-accordion-${idx}`; accordionRoot.id = baseID; const headings = accordionRoot.querySelectorAll('.accordion-header'); if (!headings.length) { return; } const collapseElements = accordionRoot.querySelectorAll('.accordion-collapse'); headings.forEach((headingElement, idx) => { const headingID = `${baseID}-heading-${idx}`; const targetID = `${baseID}-target-${idx}`; headingElement.id = headingID; const headingButton = headingElement.querySelector('.accordion-button'); if (!headingButton) { return; } headingButton.type = 'button'; headingButton.dataset['bsToggle'] = 'collapse'; headingButton.dataset['bsTarget'] = `#${targetID}`; headingButton.setAttribute('aria-expanded', true); headingButton.setAttribute('aria-controls', targetID); headingButton.setAttribute('role', 'button'); if (!collapseElements[idx].classList.contains('show')) { headingButton.classList.add('collapsed'); } collapseElements[idx].id = targetID; collapseElements[idx].setAttribute('aria-labelledby', headingID); }); new bootstrap.Collapse(accordionRoot); }; const initAccordions = () => { const accordions = document.querySelectorAll('section.page__section div.accordion'); if (!accordions.length) { return; } let accordionIndex = 0; accordions.forEach((accordion) => { doInit(accordion, accordionIndex); accordionIndex += 1; }); }; document.addEventListener('DOMContentLoaded', initAccordions) })(); </script> <script src="https://dirms4qsy6412.cloudfront.net/assets/grapesjs-tabs-f0b094476ecf56695b765f533e437303138b1e0824d993c50ff672e16dcccd8f.js"></script> <script src="https://dirms4qsy6412.cloudfront.net/assets/legacy-chart/d3.v4.min-41cfecdf7c41476e805de7afacf4aacdd1a4be6947fbecf95217e947ebc2faf5.js"></script> <script src="https://dirms4qsy6412.cloudfront.net/assets/legacy-chart/visualize-d-06443fdef48364af6635f0d1d3535da26910671f6f6a680c531eff0e54ed595f.js"></script> <script src="https://dirms4qsy6412.cloudfront.net/assets/momentjs/moment-b955adb4137f92dd932ff2c3179ce60cb5e1daed5fcc4423f95cf17df02b4d68.js"></script> <script src="https://dirms4qsy6412.cloudfront.net/assets/momentjs/moment-timezone-with-data-10-year-range-dd05517070a46fa0052f9e706803d57a4fc38c1a223137ab480369e6308ba8d4.js"></script> <script src="https://dirms4qsy6412.cloudfront.net/assets/calendar-256ba38a1da92b24c057388ff6623eddd4cf1498f51d1a389cc4dfac501ab87c.js"></script> <script src="https://dirms4qsy6412.cloudfront.net/assets/nv-developer-menu-09b6a95e79b8d8d44b0f1ac794e39d5adac82391d128f6d4d39715826a860020.js"></script> <script> let menuLocale = 'en'; if (menuLocale == 'en') { menuLocale = 'en-US'; } function mountHeader(data = false) { let options = { baseURL: window.location.origin, signedIn: false, locale: menuLocale }; if (data) { options.secondaryMenu = data; } options.showMembershipCardLink = true; new NVDeveloperHeader({ target: document.getElementById('header'), props: options }); } function mountFooter(data = false) { let options = { menu: data, locale: menuLocale }; new NVDeveloperFooter({ target: document.getElementById('footer'), props: options }); } let url = 'd29g4g2dyqv443.cloudfront.net'; let headerMenuURL = "https://d29g4g2dyqv443.cloudfront.net/menu/en-US/header-secondary.json"; fetch(headerMenuURL) .then(response => response.json()) .then(data => { mountHeader(data); }) .catch((error) => { mountHeader(); window.nv.tracing.addError('menu', error); }); fetch(`https://${url}/menu/${menuLocale}/footer.json`) .then(response => response.json()) .then(data => { mountFooter(data); }) .catch((error) => { mountFooter(); window.nv.tracing.addError('menu', error); }); </script> <script src="https://www.datadoghq-browser-agent.com/us1/v5/datadog-rum.js"></script> <script> let silentAuthHost = 'www.nvidia.com'; let crossOriginPageUrl = `https://${silentAuthHost}/auth/hints/`; function readHint() { return new Promise((resolve) => { const { origin: targetOrigin } = new URL(crossOriginPageUrl); const iframe = document.createElement('iframe'); iframe.hidden = true; iframe.src = crossOriginPageUrl; function responseHandler(event) { if (event.origin === targetOrigin) { iframe.parentNode.removeChild(iframe); return resolve(event.data); } } window.addEventListener('message', responseHandler, { once: true }); iframe.onload = () => { iframe.contentWindow.postMessage({ type: 'read' }, targetOrigin); } document.body.appendChild(iframe); }); } function writeHint(login_hint, idp_id, timestamp, sub) { const { origin: targetOrigin } = new URL(crossOriginPageUrl); const iframe = document.createElement('iframe'); iframe.hidden = true; iframe.src = crossOriginPageUrl; iframe.onload = () => { const message = { type: 'write', login_hint, idp_id, timestamp, sub }; iframe.contentWindow.postMessage(message, targetOrigin); } document.body.appendChild(iframe); } function deleteHint() { const { origin: targetOrigin } = new URL(crossOriginPageUrl); const iframe = document.createElement('iframe'); iframe.hidden = true; iframe.src = crossOriginPageUrl; iframe.onload = () => { iframe.contentWindow.postMessage({ type: 'delete' }, targetOrigin); } document.body.appendChild(iframe); } </script> <script>_satellite.pageBottom();</script> <script src="https://api-prod.nvidia.com/search/nvidia-gallery-widget.js"></script> <script src="https://dirms4qsy6412.cloudfront.net/assets/nv-gallery-widget-3773782f8ce6c8c8a941c2b9081c011da255a54832177fb8bd2e6c7967d37182.js"></script> <script src="https://dirms4qsy6412.cloudfront.net/packs/js/runtime-503119e3bfeec75056bc.js" defer="defer"></script> <script src="https://dirms4qsy6412.cloudfront.net/packs/js/692-70104789368a40f2d231.js" defer="defer"></script> <script src="https://dirms4qsy6412.cloudfront.net/packs/js/341-3761d2892158034dde54.js" defer="defer"></script> <script src="https://dirms4qsy6412.cloudfront.net/packs/js/798-8f26177f1189c7399fb3.js" defer="defer"></script> <script src="https://dirms4qsy6412.cloudfront.net/packs/js/866-f9c34b19d1b60b883caf.js" defer="defer"></script> <script src="https://dirms4qsy6412.cloudfront.net/packs/js/311-033b6299b51897e65419.js" defer="defer"></script> <script src="https://dirms4qsy6412.cloudfront.net/packs/js/252-f83b27d9f72fef366bc7.js" defer="defer"></script> <script src="https://dirms4qsy6412.cloudfront.net/packs/js/367-0b2e82a8016bebbc82b5.js" defer="defer"></script> <script src="https://dirms4qsy6412.cloudfront.net/packs/js/900-34f3bf570904cbfb5a16.js" defer="defer"></script> <script src="https://dirms4qsy6412.cloudfront.net/packs/js/application-54bf18784eb1ee5cdece.js" defer="defer"></script> <script src="https://dirms4qsy6412.cloudfront.net/packs/js/ls_track-4ba11c63b23b3f4ff0d5.js" defer="defer"></script> </body> </html>