inference-endpoints/pr_101/en/_app/immutable/nodes/4.d416eded.js

import{s as ct,n as ft,o as ht}from"../chunks/scheduler.389d799c.js";import{S as gt,i as yt,g as o,s as a,r as l,A as $t,h as r,f as n,c as s,j as ut,u as p,x as h,k as mt,y as wt,a as i,v as d,d as u,t as m,w as c}from"../chunks/index.8f81d18f.js";import{C as Tt}from"../chunks/CodeBlock.3845caa1.js";import{H as f,E as It}from"../chunks/EditOnGithub.33306dfe.js";function vt(Ve){let g,ae,ne,se,y,oe,$,le,w,Ye="A: Inference Endpoints are currently available on AWS in us-east-1 (N. Virginia) & eu-west-1 (Ireland), on Azure in eastus (Virginia), and on GCP in us-east4 (Virginia). If you need to deploy in a different region, please let us know.",re,T,pe,I,Ge="A: No, you cannot access the instance hosting your Endpoint. But if you are missing information or need more insights on the machine where the Endpoint is running, please contact us.",de,v,ue,b,Ze="A: No, when creating a Private Endpoint (a Hugging Face Inference Endpoint linked to your VPC via AWS/Azure PrivateLink), you can only see the ENI in your VPC where the Endpoint is available.",me,C,ce,q,Oe='A: It depends on the Task. The <a href="/docs/inference-endpoints/supported_tasks">supported Tasks</a> are using the transformers, sentence-transformers, or diffusers pipelines under the hood. If your Task pipeline supports batching, e.g. Zero-Shot Classification then batch inference is supported. In any case, you can always create your own <a href="/docs/inference-endpoints/guides/custom_handler">inference handler</a> and implement batching.',fe,x,he,E,Re="A: The Endpoints are scaled automatically for you, the only information you need to provide is a min replica target and a max replica target. Then the system will scale your Endpoint based on the load. Scaling to zero is supported with a variety of timing options.",ge,k,ye,J,Xe="A: Yes, your Endpoint will always stay available/up with the number of min replicas defined in the Advanced configuration.",$e,Q,we,M,Ke='A:  Yes, you can deploy any repository from the <a href="https://huggingface.co/models" rel="nofollow">Hugging Face Hub</a> and if your task/model/framework is not supported out of the box, you can <a href="/docs/inference-endpoints/guides/custom_handler">create your own inference handler</a> and then deploy your model to an Endpoint.',Te,P,Ie,A,et="A: Dedicated Endpoints are billed based on the compute hours of your Running Endpoints, and the associated instance types. We may add usage costs for load balancers and Private Links in the future.",ve,_,be,j,tt="A: Yes, data is encrypted during transit with TLS/SSL.",Ce,H,qe,L,nt='A: There are several ways to reduce the latency of your Endpoint. One is to deploy your Endpoint in a region close to your application to reduce the network overhead. Another is to optimize your model using <a href="https://huggingface.co/docs/optimum/index" rel="nofollow">Hugging Face Optimum</a> before creating your Endpoint. If you need help or have more questions about reducing latency, please contact us.',xe,S,Ee,U,it='A: You can currently monitor your Endpoint through the <a href="https://ui.endpoints.huggingface.co/endpoints" rel="nofollow">🤗 Inference Endpoints web application</a>, where you have access to the <a href="/docs/inference-endpoints/guides/logs">Logs of your Endpoints</a> as well as a <a href="/docs/inference-endpoints/guides/metrics">metrics dashboard</a>. If you need programmatic access or more information, please contact us.',ke,W,Je,B,at="A: Please contact us if you feel your model would do better on a different instance type than what is listed.",Qe,z,Me,N,st='A: You can invalidate existing personal tokens and create new ones in your settings here: <a href="https://huggingface.co/settings/tokens" rel="nofollow">https://huggingface.co/settings/tokens</a>. Note that fine-grained tokens <em>are</em> supported in Inference Endpoints - please consider using them!',Pe,D,Ae,F,ot="A: This is now possible in the UI, or via the API:",_e,V,je,Y,He,G,lt='A: Yes! Please check out our <a href="https://huggingface.co/docs/text-generation-inference/index" rel="nofollow">TGI documentation</a> and this <a href="https://www.youtube.com/watch?v=jlMAX2Oaht0" rel="nofollow">video</a> on TGI deploys.',Le,Z,Se,O,rt="A: To help mitigate service interruptions on an Endpoint that needs to be highly available, please make sure to use at least 2 replicas, ie min replicas set to 2.",Ue,R,We,X,pt='A: The Inference API (Serverless) is a solution to easily explore and evaluate models. For larger volumes of requests, or if you need guaranteed latency/performance, use <a href="https://ui.endpoints.huggingface.co/new" rel="nofollow">Inference Endpoints (Dedicated)</a> to easily deploy your models on dedicated, fully-managed infrastructure.',Be,K,ze,ee,dt="A: This usually means either the port mapping is incorrect or the <code>/health</code> route is missing. Ensure your app is listening on port 5000 and that the Docker container is exposing port 5000 externally. Additionally, confirm that you have a /health route implemented in your app that returns a status code 200, as this is how we check if your service is ready.",Ne,te,De,ie,Fe;return y=new f({props:{title:"FAQs",local:"faqs",headingTag:"h1"}}),$=new f({props:{title:"Q: In which regions are Inference Endpoints available?",local:"q-in-which-regions-are-inference-endpoints-available",headingTag:"h3"}}),T=new f({props:{title:"Q: Can I access the instance my Endpoint is running on?",local:"q-can-i-access-the-instance-my-endpoint-is-running-on",headingTag:"h3"}}),v=new f({props:{title:"Q: Can I see my Private Endpoint running on my VPC account?",local:"q-can-i-see-my-private-endpoint-running-on-my-vpc-account",headingTag:"h3"}}),C=new f({props:{title:"Q: Can I run inference in batches?",local:"q-can-i-run-inference-in-batches",headingTag:"h3"}}),x=new f({props:{title:"Q: How can I scale my deployment?",local:"q-how-can-i-scale-my-deployment",headingTag:"h3"}}),k=new f({props:{title:"Q: Will my endpoint still be running if no more requests are processed?",local:"q-will-my-endpoint-still-be-running-if-no-more-requests-are-processed",headingTag:"h3"}}),Q=new f({props:{title:"Q: I would like to deploy a model which is not in the supported tasks, is this possible?",local:"q-i-would-like-to-deploy-a-model-which-is-not-in-the-supported-tasks-is-this-possible",headingTag:"h3"}}),P=new f({props:{title:"Q: How much does it cost to run my Endpoint?",local:"q-how-much-does-it-cost-to-run-my-endpoint",headingTag:"h3"}}),_=new f({props:{title:"Q: Is the data transiting to the Endpoint encrypted?",local:"q-is-the-data-transiting-to-the-endpoint-encrypted",headingTag:"h3"}}),H=new f({props:{title:"Q: How can I reduce the latency of my Endpoint?",local:"q-how-can-i-reduce-the-latency-of-my-endpoint",headingTag:"h3"}}),S=new f({props:{title:"Q: How do I monitor my deployed Endpoint?",local:"q-how-do-i-monitor-my-deployed-endpoint",headingTag:"h3"}}),W=new f({props:{title:"Q: What if I would like to deploy to a different instance type that is not listed?",local:"q-what-if-i-would-like-to-deploy-to-a-different-instance-type-that-is-not-listed",headingTag:"h3"}}),z=new f({props:{title:"Q: I accidentally leaked my token. Do I need to delete my endpoint?",local:"q-i-accidentally-leaked-my-token-do-i-need-to-delete-my-endpoint",headingTag:"h3"}}),D=new f({props:{title:"Q: I need to add a custom environment variable (default or secrets) to my endpoint. How can I do this?",local:"q-i-need-to-add-a-custom-environment-variable-default-or-secrets-to-my-endpoint-how-can-i-do-this",headingTag:"h3"}}),V=new Tt({props:{code:"JTdCJTBBJTIwJTIwJTIybW9kZWwlMjIlM0ElMjAlN0IlMEElMjAlMjAlMjAlMjAlMjJpbWFnZSUyMiUzQSUyMCU3QiUwQSUyMCUyMCUyMCUyMCUyMCUyMCUyMmh1Z2dpbmdmYWNlJTIyJTNBJTIwJTdCJTBBJTIwJTIwJTIwJTIwJTIwJTIwJTIwJTIwJTIyZW52JTIyJTNBJTIwJTdCJTIwJTIydmFyMSUyMiUzQSUyMCUyMnZhbHVlJTIyJTIwJTdEJTBBJTIwJTIwJTIwJTIwJTIwJTIwJTdEJTBBJTIwJTIwJTIwJTIwJTdEJTJDJTBBJTdE",highlighted:`<span class="hljs-punctuation">{</span>
  <span class="hljs-attr">&quot;model&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span>
    <span class="hljs-attr">&quot;image&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span>
      <span class="hljs-attr">&quot;huggingface&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span>
        <span class="hljs-attr">&quot;env&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> <span class="hljs-attr">&quot;var1&quot;</span><span class="hljs-punctuation">:</span> <span class="hljs-string">&quot;value&quot;</span> <span class="hljs-punctuation">}</span>
      <span class="hljs-punctuation">}</span>
    <span class="hljs-punctuation">}</span><span class="hljs-punctuation">,</span>
<span class="hljs-punctuation">}</span>`,wrap:!1}}),Y=new f({props:{title:"Q: I’m using the text-generation-inference container type for my Endpoint. Is there more information about using TGI?",local:"q-im-using-the-text-generation-inference-container-type-for-my-endpoint-is-there-more-information-about-using-tgi",headingTag:"h3"}}),Z=new f({props:{title:"Q: I’m sometimes running into a 503 error on a running endpoint in production. What can I do?",local:"q-im-sometimes-running-into-a-503-error-on-a-running-endpoint-in-production-what-can-i-do",headingTag:"h3"}}),R=new f({props:{title:"Q: What’s the difference between Dedicated and Serverless Endpoints?",local:"q-whats-the-difference-between-dedicated-and-serverless-endpoints",headingTag:"h3"}}),K=new f({props:{title:"Q: I can see from the logs that my endpoint is running but the status is stuck at “initializing”",local:"q-i-can-see-from-the-logs-that-my-endpoint-is-running-but-the-status-is-stuck-at-initializing",headingTag:"h3"}}),te=new It({props:{source:"https://github.com/huggingface/hf-endpoints-documentation/blob/main/docs/source/faq.mdx"}}),{c(){g=o("meta"),ae=a(),ne=o("p"),se=a(),l(y.$$.fragment),oe=a(),l($.$$.fragment),le=a(),w=o("p"),w.textContent=Ye,re=a(),l(T.$$.fragment),pe=a(),I=o("p"),I.textContent=Ge,de=a(),l(v.$$.fragment),ue=a(),b=o("p"),b.textContent=Ze,me=a(),l(C.$$.fragment),ce=a(),q=o("p"),q.innerHTML=Oe,fe=a(),l(x.$$.fragment),he=a(),E=o("p"),E.textContent=Re,ge=a(),l(k.$$.fragment),ye=a(),J=o("p"),J.textContent=Xe,$e=a(),l(Q.$$.fragment),we=a(),M=o("p"),M.innerHTML=Ke,Te=a(),l(P.$$.fragment),Ie=a(),A=o("p"),A.textContent=et,ve=a(),l(_.$$.fragment),be=a(),j=o("p"),j.textContent=tt,Ce=a(),l(H.$$.fragment),qe=a(),L=o("p"),L.innerHTML=nt,xe=a(),l(S.$$.fragment),Ee=a(),U=o("p"),U.innerHTML=it,ke=a(),l(W.$$.fragment),Je=a(),B=o("p"),B.textContent=at,Qe=a(),l(z.$$.fragment),Me=a(),N=o("p"),N.innerHTML=st,Pe=a(),l(D.$$.fragment),Ae=a(),F=o("p"),F.textContent=ot,_e=a(),l(V.$$.fragment),je=a(),l(Y.$$.fragment),He=a(),G=o("p"),G.innerHTML=lt,Le=a(),l(Z.$$.fragment),Se=a(),O=o("p"),O.textContent=rt,Ue=a(),l(R.$$.fragment),We=a(),X=o("p"),X.innerHTML=pt,Be=a(),l(K.$$.fragment),ze=a(),ee=o("p"),ee.innerHTML=dt,Ne=a(),l(te.$$.fragment),De=a(),ie=o("p"),this.h()},l(e){const t=$t("svelte-u9bgzb",document.head);g=r(t,"META",{name:!0,content:!0}),t.forEach(n),ae=s(e),ne=r(e,"P",{}),ut(ne).forEach(n),se=s(e),p(y.$$.fragment,e),oe=s(e),p($.$$.fragment,e),le=s(e),w=r(e,"P",{"data-svelte-h":!0}),h(w)!=="svelte-1j304g2"&&(w.textContent=Ye),re=s(e),p(T.$$.fragment,e),pe=s(e),I=r(e,"P",{"data-svelte-h":!0}),h(I)!=="svelte-70k5u1"&&(I.textContent=Ge),de=s(e),p(v.$$.fragment,e),ue=s(e),b=r(e,"P",{"data-svelte-h":!0}),h(b)!=="svelte-1yippg2"&&(b.textContent=Ze),me=s(e),p(C.$$.fragment,e),ce=s(e),q=r(e,"P",{"data-svelte-h":!0}),h(q)!=="svelte-19pq2oe"&&(q.innerHTML=Oe),fe=s(e),p(x.$$.fragment,e),he=s(e),E=r(e,"P",{"data-svelte-h":!0}),h(E)!=="svelte-8t8fdi"&&(E.textContent=Re),ge=s(e),p(k.$$.fragment,e),ye=s(e),J=r(e,"P",{"data-svelte-h":!0}),h(J)!=="svelte-1o8fodi"&&(J.textContent=Xe),$e=s(e),p(Q.$$.fragment,e),we=s(e),M=r(e,"P",{"data-svelte-h":!0}),h(M)!=="svelte-1ikn0zc"&&(M.innerHTML=Ke),Te=s(e),p(P.$$.fragment,e),Ie=s(e),A=r(e,"P",{"data-svelte-h":!0}),h(A)!=="svelte-tl2ufl"&&(A.textContent=et),ve=s(e),p(_.$$.fragment,e),be=s(e),j=r(e,"P",{"data-svelte-h":!0}),h(j)!=="svelte-10encps"&&(j.textContent=tt),Ce=s(e),p(H.$$.fragment,e),qe=s(e),L=r(e,"P",{"data-svelte-h":!0}),h(L)!=="svelte-tgkqd1"&&(L.innerHTML=nt),xe=s(e),p(S.$$.fragment,e),Ee=s(e),U=r(e,"P",{"data-svelte-h":!0}),h(U)!=="svelte-1ppk556"&&(U.innerHTML=it),ke=s(e),p(W.$$.fragment,e),Je=s(e),B=r(e,"P",{"data-svelte-h":!0}),h(B)!=="svelte-bl2jeb"&&(B.textContent=at),Qe=s(e),p(z.$$.fragment,e),Me=s(e),N=r(e,"P",{"data-svelte-h":!0}),h(N)!=="svelte-sn4lhc"&&(N.innerHTML=st),Pe=s(e),p(D.$$.fragment,e),Ae=s(e),F=r(e,"P",{"data-svelte-h":!0}),h(F)!=="svelte-qwm1nw"&&(F.textContent=ot),_e=s(e),p(V.$$.fragment,e),je=s(e),p(Y.$$.fragment,e),He=s(e),G=r(e,"P",{"data-svelte-h":!0}),h(G)!=="svelte-enpakd"&&(G.innerHTML=lt),Le=s(e),p(Z.$$.fragment,e),Se=s(e),O=r(e,"P",{"data-svelte-h":!0}),h(O)!=="svelte-1iwtr3j"&&(O.textContent=rt),Ue=s(e),p(R.$$.fragment,e),We=s(e),X=r(e,"P",{"data-svelte-h":!0}),h(X)!=="svelte-wbdt7p"&&(X.innerHTML=pt),Be=s(e),p(K.$$.fragment,e),ze=s(e),ee=r(e,"P",{"data-svelte-h":!0}),h(ee)!=="svelte-t0ag6s"&&(ee.innerHTML=dt),Ne=s(e),p(te.$$.fragment,e),De=s(e),ie=r(e,"P",{}),ut(ie).forEach(n),this.h()},h(){mt(g,"name","hf:doc:metadata"),mt(g,"content",bt)},m(e,t){wt(document.head,g),i(e,ae,t),i(e,ne,t),i(e,se,t),d(y,e,t),i(e,oe,t),d($,e,t),i(e,le,t),i(e,w,t),i(e,re,t),d(T,e,t),i(e,pe,t),i(e,I,t),i(e,de,t),d(v,e,t),i(e,ue,t),i(e,b,t),i(e,me,t),d(C,e,t),i(e,ce,t),i(e,q,t),i(e,fe,t),d(x,e,t),i(e,he,t),i(e,E,t),i(e,ge,t),d(k,e,t),i(e,ye,t),i(e,J,t),i(e,$e,t),d(Q,e,t),i(e,we,t),i(e,M,t),i(e,Te,t),d(P,e,t),i(e,Ie,t),i(e,A,t),i(e,ve,t),d(_,e,t),i(e,be,t),i(e,j,t),i(e,Ce,t),d(H,e,t),i(e,qe,t),i(e,L,t),i(e,xe,t),d(S,e,t),i(e,Ee,t),i(e,U,t),i(e,ke,t),d(W,e,t),i(e,Je,t),i(e,B,t),i(e,Qe,t),d(z,e,t),i(e,Me,t),i(e,N,t),i(e,Pe,t),d(D,e,t),i(e,Ae,t),i(e,F,t),i(e,_e,t),d(V,e,t),i(e,je,t),d(Y,e,t),i(e,He,t),i(e,G,t),i(e,Le,t),d(Z,e,t),i(e,Se,t),i(e,O,t),i(e,Ue,t),d(R,e,t),i(e,We,t),i(e,X,t),i(e,Be,t),d(K,e,t),i(e,ze,t),i(e,ee,t),i(e,Ne,t),d(te,e,t),i(e,De,t),i(e,ie,t),Fe=!0},p:ft,i(e){Fe||(u(y.$$.fragment,e),u($.$$.fragment,e),u(T.$$.fragment,e),u(v.$$.fragment,e),u(C.$$.fragment,e),u(x.$$.fragment,e),u(k.$$.fragment,e),u(Q.$$.fragment,e),u(P.$$.fragment,e),u(_.$$.fragment,e),u(H.$$.fragment,e),u(S.$$.fragment,e),u(W.$$.fragment,e),u(z.$$.fragment,e),u(D.$$.fragment,e),u(V.$$.fragment,e),u(Y.$$.fragment,e),u(Z.$$.fragment,e),u(R.$$.fragment,e),u(K.$$.fragment,e),u(te.$$.fragment,e),Fe=!0)},o(e){m(y.$$.fragment,e),m($.$$.fragment,e),m(T.$$.fragment,e),m(v.$$.fragment,e),m(C.$$.fragment,e),m(x.$$.fragment,e),m(k.$$.fragment,e),m(Q.$$.fragment,e),m(P.$$.fragment,e),m(_.$$.fragment,e),m(H.$$.fragment,e),m(S.$$.fragment,e),m(W.$$.fragment,e),m(z.$$.fragment,e),m(D.$$.fragment,e),m(V.$$.fragment,e),m(Y.$$.fragment,e),m(Z.$$.fragment,e),m(R.$$.fragment,e),m(K.$$.fragment,e),m(te.$$.fragment,e),Fe=!1},d(e){e&&(n(ae),n(ne),n(se),n(oe),n(le),n(w),n(re),n(pe),n(I),n(de),n(ue),n(b),n(me),n(ce),n(q),n(fe),n(he),n(E),n(ge),n(ye),n(J),n($e),n(we),n(M),n(Te),n(Ie),n(A),n(ve),n(be),n(j),n(Ce),n(qe),n(L),n(xe),n(Ee),n(U),n(ke),n(Je),n(B),n(Qe),n(Me),n(N),n(Pe),n(Ae),n(F),n(_e),n(je),n(He),n(G),n(Le),n(Se),n(O),n(Ue),n(We),n(X),n(Be),n(ze),n(ee),n(Ne),n(De),n(ie)),n(g),c(y,e),c($,e),c(T,e),c(v,e),c(C,e),c(x,e),c(k,e),c(Q,e),c(P,e),c(_,e),c(H,e),c(S,e),c(W,e),c(z,e),c(D,e),c(V,e),c(Y,e),c(Z,e),c(R,e),c(K,e),c(te,e)}}}const bt='{"title":"FAQs","local":"faqs","sections":[{"title":"Q: In which regions are Inference Endpoints available?","local":"q-in-which-regions-are-inference-endpoints-available","sections":[],"depth":3},{"title":"Q: Can I access the instance my Endpoint is running on?","local":"q-can-i-access-the-instance-my-endpoint-is-running-on","sections":[],"depth":3},{"title":"Q: Can I see my Private Endpoint running on my VPC account?","local":"q-can-i-see-my-private-endpoint-running-on-my-vpc-account","sections":[],"depth":3},{"title":"Q: Can I run inference in batches?","local":"q-can-i-run-inference-in-batches","sections":[],"depth":3},{"title":"Q: How can I scale my deployment?","local":"q-how-can-i-scale-my-deployment","sections":[],"depth":3},{"title":"Q: Will my endpoint still be running if no more requests are processed?","local":"q-will-my-endpoint-still-be-running-if-no-more-requests-are-processed","sections":[],"depth":3},{"title":"Q: I would like to deploy a model which is not in the supported tasks, is this possible?","local":"q-i-would-like-to-deploy-a-model-which-is-not-in-the-supported-tasks-is-this-possible","sections":[],"depth":3},{"title":"Q: How much does it cost to run my Endpoint?","local":"q-how-much-does-it-cost-to-run-my-endpoint","sections":[],"depth":3},{"title":"Q: Is the data transiting to the Endpoint encrypted?","local":"q-is-the-data-transiting-to-the-endpoint-encrypted","sections":[],"depth":3},{"title":"Q: How can I reduce the latency of my Endpoint?","local":"q-how-can-i-reduce-the-latency-of-my-endpoint","sections":[],"depth":3},{"title":"Q: How do I monitor my deployed Endpoint?","local":"q-how-do-i-monitor-my-deployed-endpoint","sections":[],"depth":3},{"title":"Q: What if I would like to deploy to a different instance type that is not listed?","local":"q-what-if-i-would-like-to-deploy-to-a-different-instance-type-that-is-not-listed","sections":[],"depth":3},{"title":"Q: I accidentally leaked my token. Do I need to delete my endpoint?","local":"q-i-accidentally-leaked-my-token-do-i-need-to-delete-my-endpoint","sections":[],"depth":3},{"title":"Q: I need to add a custom environment variable (default or secrets) to my endpoint. How can I do this?","local":"q-i-need-to-add-a-custom-environment-variable-default-or-secrets-to-my-endpoint-how-can-i-do-this","sections":[],"depth":3},{"title":"Q: I’m using the text-generation-inference container type for my Endpoint. Is there more information about using TGI?","local":"q-im-using-the-text-generation-inference-container-type-for-my-endpoint-is-there-more-information-about-using-tgi","sections":[],"depth":3},{"title":"Q: I’m sometimes running into a 503 error on a running endpoint in production. What can I do?","local":"q-im-sometimes-running-into-a-503-error-on-a-running-endpoint-in-production-what-can-i-do","sections":[],"depth":3},{"title":"Q: What’s the difference between Dedicated and Serverless Endpoints?","local":"q-whats-the-difference-between-dedicated-and-serverless-endpoints","sections":[],"depth":3},{"title":"Q: I can see from the logs that my endpoint is running but the status is stuck at “initializing”","local":"q-i-can-see-from-the-logs-that-my-endpoint-is-running-but-the-status-is-stuck-at-initializing","sections":[],"depth":3}],"depth":1}';function Ct(Ve){return ht(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Jt extends gt{constructor(g){super(),yt(this,g,Ct,vt,ct,{})}}export{Jt as component};