inference-endpoints/pr_156/en/_app/immutable/nodes/2.fdcd3c0d.js

import{s as Ee,n as Pe,o as He}from"../chunks/scheduler.eb244325.js";import{S as Me,i as Ae,e as a,s as o,c as M,h as ke,a as s,d as n,b as l,f as Le,g as A,j as r,k as Ie,l as Se,m as i,n as k,t as S,o as z,p as G}from"../chunks/index.661680a1.js";import{C as ze,H as pe,E as Ge}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.93434bbb.js";function je(ue){let p,U,j,F,u,O,f,W,c,fe=`Inference Endpoints is a managed service to deploy your AI model to production. The infrastructure is managed and configured such that
you can focus on building your AI application.`,D,m,ce="To get an AI model into production, you need three key components:",R,d,me=`<li><p><strong>Model Weights and Artifacts</strong>: These are the trained parameters and files that define your AI model, stored and versioned on the
Hugging Face Hub.</p></li> <li><p><strong>Inference Engine</strong>: This is the software that loads and runs your model to generate predictions. Popular engines include vLLM, TGI, and
others, each optimized for different use cases and performance needs.</p></li> <li><p><strong>Production Infrastructure</strong>: This is what Inference Endpoints is. A scalable, secure, and reliable environment where your model runs—handling
requests, scaling with demand, and ensuring uptime.</p></li>`,Y,h,de=`Inference Endpoints brings all these pieces together into a single managed service. You choose your model from the Hub, select the
inference engine, and Inference Endpoints takes care of the rest—provisioning infrastructure, deploying your model, and making it
accessible via a simple API. This lets you focus on building your application, while we handle the complexity of production AI deployment.`,B,g,he='<img src="https://raw.githubusercontent.com/huggingface/hf-endpoints-documentation/main/assets/about.png" alt="about"/>',J,v,K,y,ge="To achieve that we’ve made Inference Endpoints the central place to deploy high performance and open-source Inference Engines.",N,x,ve="Currently we have native support for:",Q,$,ye="<li>vLLM</li> <li>Text-generation-inference (TGI)</li> <li>SGLang</li> <li>llama.cpp</li> <li>and Text-embeddings-inference (TEI)</li>",V,b,xe=`For the natively supported engines we try to set sensible defaults, expose the most relevant configuration settings and collaborate closely
with the teams maintaining the Inference Engines to make sure they are optimized for production performance.`,X,C,$e='If you don’t find your favourite engine here, please reach out to us at <a href="api-enterprise@huggingface.co">api-enterprise@huggingface.co</a>.',Z,T,ee,w,be=`When you deploy an Inference Endpoint, under the hood your selected inference engine (like vLLM, TGI, SGLang, etc.) is packaged
and launched as a prebuilt Docker container. This container includes the inference engine software, your chosen model
weights and artifacts (downloaded directly from the Hugging Face Hub), and any configuration or environment variables you specify.`,te,_,Ce=`We manage the full lifecycle of these containers: starting, stopping, scaling (including autoscaling and scale-to-zero),
and monitoring them for health and performance. This orchestration is completely managed for you, so you don’t have to worry about
the complexities of containerization, networking, or cloud resource management.`,ne,L,ie,I,Te='For more features consider subscribing to <a href="https://huggingface.co/enterprise" rel="nofollow">Team or Enterprise</a>.',oe,E,we="It gives your organization more control over access controls, dedicated support and more. Features include:",le,P,_e="<li>Higher quotas for the most performant GPUs</li> <li>Single Sign-on (SSO)</li> <li>Access to Audit Logs</li> <li>Manage teams and projects access controls with Resource Groups</li> <li>Private storage for your repositories</li> <li>Disable the ability to create public repositories (or make repositories private by default)</li> <li>You can request a quote for a contract-based-invoice which allows for more payment options + prepaid credits</li> <li>and more!</li>",ae,H,se,q,re;return u=new ze({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),f=new pe({props:{title:"About Inference Endpoints",local:"about-inference-endpoints",headingTag:"h1"}}),v=new pe({props:{title:"Inference Engines",local:"inference-engines",headingTag:"h2"}}),T=new pe({props:{title:"Under the Hood",local:"under-the-hood",headingTag:"h2"}}),L=new pe({props:{title:"Enterprise or Team Subscription",local:"enterprise-or-team-subscription",headingTag:"h2"}}),H=new Ge({props:{source:"https://github.com/huggingface/hf-endpoints-documentation/blob/main/docs/source/about.md"}}),{c(){p=a("meta"),U=o(),j=a("p"),F=o(),M(u.$$.fragment),O=o(),M(f.$$.fragment),W=o(),c=a("p"),c.textContent=fe,D=o(),m=a("p"),m.textContent=ce,R=o(),d=a("ol"),d.innerHTML=me,Y=o(),h=a("p"),h.textContent=de,B=o(),g=a("p"),g.innerHTML=he,J=o(),M(v.$$.fragment),K=o(),y=a("p"),y.textContent=ge,N=o(),x=a("p"),x.textContent=ve,Q=o(),$=a("ul"),$.innerHTML=ye,V=o(),b=a("p"),b.textContent=xe,X=o(),C=a("p"),C.innerHTML=$e,Z=o(),M(T.$$.fragment),ee=o(),w=a("p"),w.textContent=be,te=o(),_=a("p"),_.textContent=Ce,ne=o(),M(L.$$.fragment),ie=o(),I=a("p"),I.innerHTML=Te,oe=o(),E=a("p"),E.textContent=we,le=o(),P=a("ul"),P.innerHTML=_e,ae=o(),M(H.$$.fragment),se=o(),q=a("p"),this.h()},l(e){const t=ke("svelte-u9bgzb",document.head);p=s(t,"META",{name:!0,content:!0}),t.forEach(n),U=l(e),j=s(e,"P",{}),Le(j).forEach(n),F=l(e),A(u.$$.fragment,e),O=l(e),A(f.$$.fragment,e),W=l(e),c=s(e,"P",{"data-svelte-h":!0}),r(c)!=="svelte-12egzkp"&&(c.textContent=fe),D=l(e),m=s(e,"P",{"data-svelte-h":!0}),r(m)!=="svelte-pjhxe6"&&(m.textContent=ce),R=l(e),d=s(e,"OL",{"data-svelte-h":!0}),r(d)!=="svelte-cejzw3"&&(d.innerHTML=me),Y=l(e),h=s(e,"P",{"data-svelte-h":!0}),r(h)!=="svelte-1y1l12u"&&(h.textContent=de),B=l(e),g=s(e,"P",{"data-svelte-h":!0}),r(g)!=="svelte-1s5ukr3"&&(g.innerHTML=he),J=l(e),A(v.$$.fragment,e),K=l(e),y=s(e,"P",{"data-svelte-h":!0}),r(y)!=="svelte-59uh5h"&&(y.textContent=ge),N=l(e),x=s(e,"P",{"data-svelte-h":!0}),r(x)!=="svelte-1ygbjmf"&&(x.textContent=ve),Q=l(e),$=s(e,"UL",{"data-svelte-h":!0}),r($)!=="svelte-1i10e71"&&($.innerHTML=ye),V=l(e),b=s(e,"P",{"data-svelte-h":!0}),r(b)!=="svelte-y0p6de"&&(b.textContent=xe),X=l(e),C=s(e,"P",{"data-svelte-h":!0}),r(C)!=="svelte-l79z0z"&&(C.innerHTML=$e),Z=l(e),A(T.$$.fragment,e),ee=l(e),w=s(e,"P",{"data-svelte-h":!0}),r(w)!=="svelte-po5x90"&&(w.textContent=be),te=l(e),_=s(e,"P",{"data-svelte-h":!0}),r(_)!=="svelte-9jxghf"&&(_.textContent=Ce),ne=l(e),A(L.$$.fragment,e),ie=l(e),I=s(e,"P",{"data-svelte-h":!0}),r(I)!=="svelte-1ne9hjb"&&(I.innerHTML=Te),oe=l(e),E=s(e,"P",{"data-svelte-h":!0}),r(E)!=="svelte-1uam4qw"&&(E.textContent=we),le=l(e),P=s(e,"UL",{"data-svelte-h":!0}),r(P)!=="svelte-1vxs7qh"&&(P.innerHTML=_e),ae=l(e),A(H.$$.fragment,e),se=l(e),q=s(e,"P",{}),Le(q).forEach(n),this.h()},h(){Ie(p,"name","hf:doc:metadata"),Ie(p,"content",qe)},m(e,t){Se(document.head,p),i(e,U,t),i(e,j,t),i(e,F,t),k(u,e,t),i(e,O,t),k(f,e,t),i(e,W,t),i(e,c,t),i(e,D,t),i(e,m,t),i(e,R,t),i(e,d,t),i(e,Y,t),i(e,h,t),i(e,B,t),i(e,g,t),i(e,J,t),k(v,e,t),i(e,K,t),i(e,y,t),i(e,N,t),i(e,x,t),i(e,Q,t),i(e,$,t),i(e,V,t),i(e,b,t),i(e,X,t),i(e,C,t),i(e,Z,t),k(T,e,t),i(e,ee,t),i(e,w,t),i(e,te,t),i(e,_,t),i(e,ne,t),k(L,e,t),i(e,ie,t),i(e,I,t),i(e,oe,t),i(e,E,t),i(e,le,t),i(e,P,t),i(e,ae,t),k(H,e,t),i(e,se,t),i(e,q,t),re=!0},p:Pe,i(e){re||(S(u.$$.fragment,e),S(f.$$.fragment,e),S(v.$$.fragment,e),S(T.$$.fragment,e),S(L.$$.fragment,e),S(H.$$.fragment,e),re=!0)},o(e){z(u.$$.fragment,e),z(f.$$.fragment,e),z(v.$$.fragment,e),z(T.$$.fragment,e),z(L.$$.fragment,e),z(H.$$.fragment,e),re=!1},d(e){e&&(n(U),n(j),n(F),n(O),n(W),n(c),n(D),n(m),n(R),n(d),n(Y),n(h),n(B),n(g),n(J),n(K),n(y),n(N),n(x),n(Q),n($),n(V),n(b),n(X),n(C),n(Z),n(ee),n(w),n(te),n(_),n(ne),n(ie),n(I),n(oe),n(E),n(le),n(P),n(ae),n(se),n(q)),n(p),G(u,e),G(f,e),G(v,e),G(T,e),G(L,e),G(H,e)}}}const qe='{"title":"About Inference Endpoints","local":"about-inference-endpoints","sections":[{"title":"Inference Engines","local":"inference-engines","sections":[],"depth":2},{"title":"Under the Hood","local":"under-the-hood","sections":[],"depth":2},{"title":"Enterprise or Team Subscription","local":"enterprise-or-team-subscription","sections":[],"depth":2}],"depth":1}';function Ue(ue){return He(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class De extends Me{constructor(p){super(),Ae(this,p,Ue,je,Ee,{})}}export{De as component};