sagemaker/pr_1706/en/_app/immutable/nodes/2.fcbc09df.js

import{s as Ge,n as De,o as Se}from"../chunks/scheduler.389d799c.js";import{S as ze,i as We,g as l,s as r,r as c,A as Re,h as o,f as n,c as i,j as Ue,u,x as s,k as Ee,y as qe,a,v as m,d,t as p,w as h}from"../chunks/index.8f81d18f.js";import{H as R,E as Be}from"../chunks/index.d407e2cc.js";function Fe(ge){let f,F,q,N,g,j,$,$e="Below you can find a listing of all the Deep Learning Containers (DLCs) available on AWS.",Q,b,be="For each supported combination of use-case (training, inference), accelerator type (CPU, GPU, Neuron), and framework (PyTorch, TGI, TEI) containers are created.",O,T,Y,y,Te="<strong>How to choose the right container for my use case?</strong>",J,x,ye='<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/sagemaker/dlc-decision-tree.png" alt="dlc-decision-tree"/>',K,v,xe='<em>Note:</em> See <a href="(https://huggingface.co/docs/sagemaker/main/en/reference/inference-toolkit)">here</a> for the list of supported task in the inference toolkit.',V,C,ve='<em>Note:</em> Browse through the Hub to see if you model is tagged <a href="https://huggingface.co/models?other=text-generation-inference" rel="nofollow">“text-generation-inference”</a> or <a href="https://huggingface.co/models?other=text-embeddings-inference" rel="nofollow">“text-embeddings-inference”</a>',X,w,Ce=`<strong>How to find the URI of my container?</strong>
The URI is built with an AWS account ID and an AWS region. Those two values need to be replaced depending on your use case.
Let’s say you want to use the training DLC for GPUs in`,Z,L,we='<li><code>dlc-aws-account-id</code>: The AWS account ID of the account that owns the ECR repository. You can find them in the <a href="https://github.com/aws/sagemaker-python-sdk/blob/e0b9d38e1e3b48647a02af23c4be54980e53dc61/src/sagemaker/image_uri_config/huggingface.json#L21" rel="nofollow">here</a></li> <li><code>region</code>: The AWS region where you want to use it.</li>',ee,P,te,_,Le="Pytorch Training DLC: For training, our DLCs are available for PyTorch via :hugging_face: Transformers. They include support for training on GPUs and AWS AI chips with libraries such as :hugging_face: TRL, Sentence Transformers, or :firecracker: Diffusers.",ne,A,Pe="<thead><tr><th>Container URI</th> <th>Accelerator</th></tr></thead> <tbody><tr><td>763104351884.dkr.ecr.us-east-1.amazonaws.com/huggingface-pytorch-training:2.5.1-transformers4.49.0-gpu-py311-cu124-ubuntu22.04</td> <td>GPU</td></tr> <tr><td>763104351884.dkr.ecr.us-east-1.amazonaws.com/huggingface-pytorch-training-neuronx:2.1.2-transformers4.48.1-neuronx-py310-sdk2.20.0-ubuntu20.04</td> <td>Neuron</td></tr></tbody>",ae,k,re,H,ie,I,_e="For inference, we have a general-purpose PyTorch inference DLC, for serving models trained with any of those frameworks mentioned before on CPU, GPU, and AWS AI chips.",le,M,Ae="<thead><tr><th>Container URI</th> <th>Accelerator</th></tr></thead> <tbody><tr><td>763104351884.dkr.ecr.us-east-1.amazonaws.com/huggingface-pytorch-inference:2.6.0-transformers4.49.0-cpu-py312-ubuntu22.04-</td> <td>CPU</td></tr> <tr><td>763104351884.dkr.ecr.us-east-1.amazonaws.com/huggingface-pytorch-inference:2.6.0-transformers4.49.0-gpu-py312-cu124-ubuntu22.04</td> <td>GPU</td></tr> <tr><td>763104351884.dkr.ecr.us-east-1.amazonaws.com/huggingface-pytorch-inference-neuronx:2.1.2-transformers4.43.2-neuronx-py310-sdk2.20.0-ubuntu20.04</td> <td>Neuron</td></tr></tbody>",oe,U,se,E,ke="There is also the Text Generation Inference (TGI) DLC for high-performance text generation of LLMs on GPU and AWS AI chips.",fe,G,He="<thead><tr><th>Container URI</th> <th>Accelerator</th></tr></thead> <tbody><tr><td>763104351884.dkr.ecr.us-east-1.amazonaws.com/huggingface-pytorch-tgi-inference:2.6.0-tgi3.2.3-gpu-py311-cu124-ubuntu22.04</td> <td>GPU</td></tr> <tr><td>763104351884.dkr.ecr.us-east-1.amazonaws.com/huggingface-pytorch-tgi-inference:2.1.2-optimum0.0.28-neuronx-py310-ubuntu22.04</td> <td>Neuron</td></tr></tbody>",ce,D,ue,S,Ie="Finally, there is a Text Embeddings Inference (TEI) DLC for high-performance serving of embedding models on CPU and GPU.",me,z,Me="<thead><tr><th>Container URI</th> <th>Accelerator</th></tr></thead> <tbody><tr><td>683313688378.dkr.ecr.us-east-1.amazonaws.com/tei-cpu:2.0.1-tei1.2.3-cpu-py310-ubuntu22.04</td> <td>CPU</td></tr> <tr><td>683313688378.dkr.ecr.us-east-1.amazonaws.com/tei:2.0.1-tei1.4.0-gpu-py310-cu122-ubuntu22.04</td> <td>GPU</td></tr></tbody>",de,W,pe,B,he;return g=new R({props:{title:"Available DLCs on AWS",local:"available-dlcs-on-aws",headingTag:"h1"}}),T=new R({props:{title:"FAQ",local:"faq",headingTag:"h2"}}),P=new R({props:{title:"Training",local:"training",headingTag:"h2"}}),k=new R({props:{title:"Inference",local:"inference",headingTag:"h2"}}),H=new R({props:{title:"Pytorch Inference DLC",local:"pytorch-inference-dlc",headingTag:"h3"}}),U=new R({props:{title:"Text Generation Inference",local:"text-generation-inference",headingTag:"h3"}}),D=new R({props:{title:"Text Embedding Inference",local:"text-embedding-inference",headingTag:"h3"}}),W=new Be({props:{source:"https://github.com/huggingface/hub-docs/blob/main/docs/sagemaker/source/dlcs/available.md"}}),{c(){f=l("meta"),F=r(),q=l("p"),N=r(),c(g.$$.fragment),j=r(),$=l("p"),$.textContent=$e,Q=r(),b=l("p"),b.textContent=be,O=r(),c(T.$$.fragment),Y=r(),y=l("p"),y.innerHTML=Te,J=r(),x=l("p"),x.innerHTML=ye,K=r(),v=l("p"),v.innerHTML=xe,V=r(),C=l("p"),C.innerHTML=ve,X=r(),w=l("p"),w.innerHTML=Ce,Z=r(),L=l("ul"),L.innerHTML=we,ee=r(),c(P.$$.fragment),te=r(),_=l("p"),_.textContent=Le,ne=r(),A=l("table"),A.innerHTML=Pe,ae=r(),c(k.$$.fragment),re=r(),c(H.$$.fragment),ie=r(),I=l("p"),I.textContent=_e,le=r(),M=l("table"),M.innerHTML=Ae,oe=r(),c(U.$$.fragment),se=r(),E=l("p"),E.textContent=ke,fe=r(),G=l("table"),G.innerHTML=He,ce=r(),c(D.$$.fragment),ue=r(),S=l("p"),S.textContent=Ie,me=r(),z=l("table"),z.innerHTML=Me,de=r(),c(W.$$.fragment),pe=r(),B=l("p"),this.h()},l(e){const t=Re("svelte-u9bgzb",document.head);f=o(t,"META",{name:!0,content:!0}),t.forEach(n),F=i(e),q=o(e,"P",{}),Ue(q).forEach(n),N=i(e),u(g.$$.fragment,e),j=i(e),$=o(e,"P",{"data-svelte-h":!0}),s($)!=="svelte-1eptnyh"&&($.textContent=$e),Q=i(e),b=o(e,"P",{"data-svelte-h":!0}),s(b)!=="svelte-nsjrcm"&&(b.textContent=be),O=i(e),u(T.$$.fragment,e),Y=i(e),y=o(e,"P",{"data-svelte-h":!0}),s(y)!=="svelte-1w3mxbc"&&(y.innerHTML=Te),J=i(e),x=o(e,"P",{"data-svelte-h":!0}),s(x)!=="svelte-1ag007e"&&(x.innerHTML=ye),K=i(e),v=o(e,"P",{"data-svelte-h":!0}),s(v)!=="svelte-dqwr3y"&&(v.innerHTML=xe),V=i(e),C=o(e,"P",{"data-svelte-h":!0}),s(C)!=="svelte-8p8z10"&&(C.innerHTML=ve),X=i(e),w=o(e,"P",{"data-svelte-h":!0}),s(w)!=="svelte-1ljwo93"&&(w.innerHTML=Ce),Z=i(e),L=o(e,"UL",{"data-svelte-h":!0}),s(L)!=="svelte-tq759t"&&(L.innerHTML=we),ee=i(e),u(P.$$.fragment,e),te=i(e),_=o(e,"P",{"data-svelte-h":!0}),s(_)!=="svelte-1yazlon"&&(_.textContent=Le),ne=i(e),A=o(e,"TABLE",{"data-svelte-h":!0}),s(A)!=="svelte-zzvgg0"&&(A.innerHTML=Pe),ae=i(e),u(k.$$.fragment,e),re=i(e),u(H.$$.fragment,e),ie=i(e),I=o(e,"P",{"data-svelte-h":!0}),s(I)!=="svelte-i6peck"&&(I.textContent=_e),le=i(e),M=o(e,"TABLE",{"data-svelte-h":!0}),s(M)!=="svelte-1jvau90"&&(M.innerHTML=Ae),oe=i(e),u(U.$$.fragment,e),se=i(e),E=o(e,"P",{"data-svelte-h":!0}),s(E)!=="svelte-1i6swpw"&&(E.textContent=ke),fe=i(e),G=o(e,"TABLE",{"data-svelte-h":!0}),s(G)!=="svelte-9qecrq"&&(G.innerHTML=He),ce=i(e),u(D.$$.fragment,e),ue=i(e),S=o(e,"P",{"data-svelte-h":!0}),s(S)!=="svelte-db04rk"&&(S.textContent=Ie),me=i(e),z=o(e,"TABLE",{"data-svelte-h":!0}),s(z)!=="svelte-1fbtly3"&&(z.innerHTML=Me),de=i(e),u(W.$$.fragment,e),pe=i(e),B=o(e,"P",{}),Ue(B).forEach(n),this.h()},h(){Ee(f,"name","hf:doc:metadata"),Ee(f,"content",Ne)},m(e,t){qe(document.head,f),a(e,F,t),a(e,q,t),a(e,N,t),m(g,e,t),a(e,j,t),a(e,$,t),a(e,Q,t),a(e,b,t),a(e,O,t),m(T,e,t),a(e,Y,t),a(e,y,t),a(e,J,t),a(e,x,t),a(e,K,t),a(e,v,t),a(e,V,t),a(e,C,t),a(e,X,t),a(e,w,t),a(e,Z,t),a(e,L,t),a(e,ee,t),m(P,e,t),a(e,te,t),a(e,_,t),a(e,ne,t),a(e,A,t),a(e,ae,t),m(k,e,t),a(e,re,t),m(H,e,t),a(e,ie,t),a(e,I,t),a(e,le,t),a(e,M,t),a(e,oe,t),m(U,e,t),a(e,se,t),a(e,E,t),a(e,fe,t),a(e,G,t),a(e,ce,t),m(D,e,t),a(e,ue,t),a(e,S,t),a(e,me,t),a(e,z,t),a(e,de,t),m(W,e,t),a(e,pe,t),a(e,B,t),he=!0},p:De,i(e){he||(d(g.$$.fragment,e),d(T.$$.fragment,e),d(P.$$.fragment,e),d(k.$$.fragment,e),d(H.$$.fragment,e),d(U.$$.fragment,e),d(D.$$.fragment,e),d(W.$$.fragment,e),he=!0)},o(e){p(g.$$.fragment,e),p(T.$$.fragment,e),p(P.$$.fragment,e),p(k.$$.fragment,e),p(H.$$.fragment,e),p(U.$$.fragment,e),p(D.$$.fragment,e),p(W.$$.fragment,e),he=!1},d(e){e&&(n(F),n(q),n(N),n(j),n($),n(Q),n(b),n(O),n(Y),n(y),n(J),n(x),n(K),n(v),n(V),n(C),n(X),n(w),n(Z),n(L),n(ee),n(te),n(_),n(ne),n(A),n(ae),n(re),n(ie),n(I),n(le),n(M),n(oe),n(se),n(E),n(fe),n(G),n(ce),n(ue),n(S),n(me),n(z),n(de),n(pe),n(B)),n(f),h(g,e),h(T,e),h(P,e),h(k,e),h(H,e),h(U,e),h(D,e),h(W,e)}}}const Ne='{"title":"Available DLCs on AWS","local":"available-dlcs-on-aws","sections":[{"title":"FAQ","local":"faq","sections":[],"depth":2},{"title":"Training","local":"training","sections":[],"depth":2},{"title":"Inference","local":"inference","sections":[{"title":"Pytorch Inference DLC","local":"pytorch-inference-dlc","sections":[],"depth":3},{"title":"Text Generation Inference","local":"text-generation-inference","sections":[],"depth":3},{"title":"Text Embedding Inference","local":"text-embedding-inference","sections":[],"depth":3}],"depth":2}],"depth":1}';function je(ge){return Se(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Je extends ze{constructor(f){super(),We(this,f,je,Fe,Ge,{})}}export{Je as component};