{"id":24954,"date":"2024-12-12T01:56:55","date_gmt":"2024-12-11T17:56:55","guid":{"rendered":"https:\/\/www.1ai.net\/?p=24954"},"modified":"2024-12-11T20:00:49","modified_gmt":"2024-12-11T12:00:49","slug":"ul-solutions-%e6%8e%a8%e5%87%ba-ai-%e6%96%87%e6%9c%ac%e7%94%9f%e6%88%90%e5%9f%ba%e5%87%86%e6%b5%8b%e8%af%95%ef%bc%8c%e6%94%af%e6%8c%81%e8%8b%b1%e4%bc%9f%e8%be%be%e3%80%81amd%e3%80%81%e8%8b%b1%e7%89%b9","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/24954.html","title":{"rendered":"UL Solutions Launches AI Text Generation Benchmark with Support for NVIDIA, AMD, Intel Graphics Cards"},"content":{"rendered":"<p>UL Solution, the developer of 3DMark, announced the launch of Procyon AI text generation on September 9, local time.<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%9f%ba%e5%87%86%e6%b5%8b%e8%af%95\" title=\"[See articles with [baseline test] labels]\" target=\"_blank\" >benchmarking<\/a>The AI gas pedal hardware's text generation capabilities are judged by synthesizing large-language AI models using a variety of different parameter scales.<\/p>\n<p>The Procyon AI Text Generation Benchmark currently supports local NVIDIA, AMD, and Intel GPUs via the DirectML Common API, as well as their own GPUs via Intel's OpenVINO (Note:<strong>Independence and integration<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%98%be%e5%8d%a1\" title=\"[Sees articles with [synthetic] labels]\" target=\"_blank\" >Graphics<\/a>all support<\/strong>(but there are differences in video memory \/ RAM capacity requirements).<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-24955\" title=\"4eceb399j00sobvzu005ld000io00c8p\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/12\/4eceb399j00sobvzu005ld000io00c8p.jpg\" alt=\"4eceb399j00sobvzu005ld000io00c8p\" width=\"672\" height=\"440\" \/><\/p>\n<p>The benchmarking<strong>Four models with varying parameter scales are now included<\/strong>(Phi-3.5-mini, Mistral-7B, Llama-3.1-8B, and Llama-2-13B), which allows for a relatively fair comparison of the performance of AI GPUs in diverse large-language model text generation use cases.<\/p>\n<p>UL Solution says the Procyon AI Text Generation Benchmark is easier to use, reduces the size of the installation compared to testing directly with a full AI model, and provides a detailed picture of how system resources are utilized when running text generation loads.<\/p>","protected":false},"excerpt":{"rendered":"<p>UL Solution, the developer of 3DMark, announced the launch of the Procyon AI Text Generation Benchmark on September 9, local time, which comprehensively judges the text generation capabilities of AI gas pedal hardware by using a wide range of large-language AI models with different parameter scales. The Procyon AI Text Generation Benchmark currently supports local NVIDIA, AMD, and Intel GPUs via the DirectML Common API, as well as Intel's own GPUs via Intel's OpenVINO (note: both discrete and integrated graphics cards are supported, but with varying video memory\/memory capacity requirements). The benchmark now includes four models of varying parameter sizes (Phi-3.5-mini, M<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[204,5192,5191],"collection":[],"class_list":["post-24954","post","type-post","status-publish","format-standard","hentry","category-news","tag-204","tag-5192","tag-5191"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/24954","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=24954"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/24954\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=24954"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=24954"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=24954"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=24954"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}