<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Voxl Pytorch Support]]></title><description><![CDATA[<p dir="auto">Hey,<br />
Pytorch supports by default CUDA(Nvidia Gpu) devices, but VOXL has a Qualcomm Adreno 530 wich is a AMD Gpu. In the Pytorch Docs there is  also a Support for AMD Gpu´s with Rocm. Does anybody know if it's possible to use Rocm on Voxl or another way to enable GPU for Pytorch?<br />
PS. I know Modal AI has a tflite Server for tensorflow Models but we already have a Model trained on Pytorch and Inference with CPU is to slow.</p>
]]></description><link>https://forum.modalai.com/topic/706/voxl-pytorch-support</link><generator>RSS for Node</generator><lastBuildDate>Wed, 19 Aug 2026 20:13:56 GMT</lastBuildDate><atom:link href="https://forum.modalai.com/topic/706.rss" rel="self" type="application/rss+xml"/><pubDate>Thu, 03 Feb 2022 10:02:43 GMT</pubDate><ttl>60</ttl><item><title><![CDATA[Reply to Voxl Pytorch Support on Mon, 07 Feb 2022 05:46:38 GMT]]></title><description><![CDATA[<p dir="auto">Thank you for your Answer yeah i will definitely look into using Tensorflow Lite</p>
]]></description><link>https://forum.modalai.com/post/3294</link><guid isPermaLink="true">https://forum.modalai.com/post/3294</guid><dc:creator><![CDATA[Philemon Benner]]></dc:creator><pubDate>Mon, 07 Feb 2022 05:46:38 GMT</pubDate></item><item><title><![CDATA[Reply to Voxl Pytorch Support on Fri, 04 Feb 2022 18:22:41 GMT]]></title><description><![CDATA[<p dir="auto"><a class="plugin-mentions-user plugin-mentions-a" href="/user/philemon-benner" aria-label="Profile: Philemon-Benner">@<bdi>Philemon-Benner</bdi></a>  In the tflite-server, we use the OpenCL backend to enable GPU support. However, according to a pytorch dev, "As Tensorflow already tentatively supports OpenCL, albeit through a proprietary compiler framework, it looks like Tensorflow is the way to go for anyone with an AMD card or, er, any CPU."</p>
<p dir="auto">That said, it may be a bit easier to convert your pytorch model over to a tflite model that can run with gpu acceleration. A good resource for this process is <a href="https://github.com/sithu31296/PyTorch-ONNX-TFLite" rel="nofollow ugc">this repo</a>, and if you are interested in some other tflite models this <a href="https://github.com/PINTO0309/PINTO_model_zoo" rel="nofollow ugc">model zoo</a> has many preconverted options.</p>
<p dir="auto">If you were to follow this conversion process, be sure to read up on <a href="https://docs.modalai.com/voxl-tflite-server/#using-your-own-models" rel="nofollow ugc">this section</a> in our documentation!</p>
]]></description><link>https://forum.modalai.com/post/3268</link><guid isPermaLink="true">https://forum.modalai.com/post/3268</guid><dc:creator><![CDATA[[[global:former-user]]]]></dc:creator><pubDate>Fri, 04 Feb 2022 18:22:41 GMT</pubDate></item><item><title><![CDATA[Reply to Voxl Pytorch Support on Thu, 03 Feb 2022 17:20:11 GMT]]></title><description><![CDATA[<p dir="auto">Thank you for your fast response. Good to know that...</p>
]]></description><link>https://forum.modalai.com/post/3250</link><guid isPermaLink="true">https://forum.modalai.com/post/3250</guid><dc:creator><![CDATA[Philemon Benner]]></dc:creator><pubDate>Thu, 03 Feb 2022 17:20:11 GMT</pubDate></item><item><title><![CDATA[Reply to Voxl Pytorch Support on Thu, 03 Feb 2022 16:58:27 GMT]]></title><description><![CDATA[<p dir="auto"><a class="plugin-mentions-user plugin-mentions-a" href="/user/philemon-benner" aria-label="Profile: Philemon-Benner">@<bdi>Philemon-Benner</bdi></a> This doesn't answer your question, but Adreno is a GPU designed by Qualcomm, not AMD.</p>
]]></description><link>https://forum.modalai.com/post/3248</link><guid isPermaLink="true">https://forum.modalai.com/post/3248</guid><dc:creator><![CDATA[Eric Katzfey]]></dc:creator><pubDate>Thu, 03 Feb 2022 16:58:27 GMT</pubDate></item></channel></rss>