Buckets:

rtrm's picture
download
raw
9.37 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Using TEI locally with an AMD GPU&quot;,&quot;local&quot;:&quot;using-tei-locally-with-an-amd-gpu&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Usage through docker&quot;,&quot;local&quot;:&quot;usage-through-docker&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
<link href="/docs/text-embeddings-inference/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
<link rel="modulepreload" href="/docs/text-embeddings-inference/main/en/_app/immutable/entry/start.5929ce5e.js">
<link rel="modulepreload" href="/docs/text-embeddings-inference/main/en/_app/immutable/chunks/scheduler.b108d059.js">
<link rel="modulepreload" href="/docs/text-embeddings-inference/main/en/_app/immutable/chunks/singletons.8ba50d2e.js">
<link rel="modulepreload" href="/docs/text-embeddings-inference/main/en/_app/immutable/chunks/paths.0433c982.js">
<link rel="modulepreload" href="/docs/text-embeddings-inference/main/en/_app/immutable/entry/app.99d3b526.js">
<link rel="modulepreload" href="/docs/text-embeddings-inference/main/en/_app/immutable/chunks/index.008de539.js">
<link rel="modulepreload" href="/docs/text-embeddings-inference/main/en/_app/immutable/nodes/0.edd78360.js">
<link rel="modulepreload" href="/docs/text-embeddings-inference/main/en/_app/immutable/nodes/6.63833e8f.js">
<link rel="modulepreload" href="/docs/text-embeddings-inference/main/en/_app/immutable/chunks/CodeBlock.3968c746.js">
<link rel="modulepreload" href="/docs/text-embeddings-inference/main/en/_app/immutable/chunks/EditOnGithub.d1c48e3d.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Using TEI locally with an AMD GPU&quot;,&quot;local&quot;:&quot;using-tei-locally-with-an-amd-gpu&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Usage through docker&quot;,&quot;local&quot;:&quot;usage-through-docker&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="using-tei-locally-with-an-amd-gpu" 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="#using-tei-locally-with-an-amd-gpu"><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>Using TEI locally with an AMD GPU</span></h1> <p data-svelte-h="svelte-1v19iux">Text-Embeddings-Inference supports the <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html" rel="nofollow">AMD GPUs officially supporting ROCm</a>, including AMD Instinct MI210, MI250, MI300 and some of the AMD Radeon series GPUs.</p> <p data-svelte-h="svelte-y2byps">To leverage AMD GPUs, Text-Embeddings-Inference relies on its Python backend, and not on the <a href="https://github.com/huggingface/candle" rel="nofollow">candle</a> backend that is used for CPU, Nvidia GPUs and Metal. The support in the python backend is more limited (Bert embeddings) but easily extensible. We welcome contributions to extend the supported models.</p> <h2 class="relative group"><a id="usage-through-docker" 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="#usage-through-docker"><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>Usage through docker</span></h2> <p data-svelte-h="svelte-qvxalu">Using docker is the recommended approach.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->DOCKER_TAG=rocm-xxx <span class="hljs-comment"># Specify the tag of the docker image to use</span>
docker run --<span class="hljs-built_in">rm</span> -it --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --net host \
--device=/dev/kfd --device=/dev/dri --group-add video --ipc=host --shm-size 32g \
ghcr.io/huggingface/text-embeddings-inference:<span class="hljs-variable">$DOCKER_TAG</span> \
--model-id sentence-transformers/all-MiniLM-L6-v2<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1qlona5">and</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->curl 127.0.0.1:80/embed \
-X POST -d <span class="hljs-string">&#x27;{&quot;inputs&quot;:&quot;What is Deep Learning?&quot;}&#x27;</span> \
-H <span class="hljs-string">&#x27;Content-Type: application/json&#x27;</span><!-- HTML_TAG_END --></pre></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/text-embeddings-inference/blob/main/docs/source/en/local_amd_gpu.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_1a9ukzg = {
assets: "/docs/text-embeddings-inference/main/en",
base: "/docs/text-embeddings-inference/main/en",
env: {}
};
const element = document.currentScript.parentElement;
const data = [null,null];
Promise.all([
import("/docs/text-embeddings-inference/main/en/_app/immutable/entry/start.5929ce5e.js"),
import("/docs/text-embeddings-inference/main/en/_app/immutable/entry/app.99d3b526.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 6],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
9.37 kB
·
Xet hash:
f356eb84827597ff5d478483ea28ec86c5ea99ac64d32007092690ddfbefe27b

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.