{"id":231262,"date":"2023-05-22T11:21:45","date_gmt":"2023-05-22T15:21:45","guid":{"rendered":"https:\/\/sftarticles.wpenginepowered.com\/es\/?p=290369"},"modified":"2025-07-01T19:08:10","modified_gmt":"2025-07-02T02:08:10","slug":"this-is-the-new-chip-that-is-building-meta-for-the-ai","status":"publish","type":"post","link":"https:\/\/cms-articles.softonic.io\/en\/this-is-the-new-chip-that-is-building-meta-for-the-ai\/","title":{"rendered":"Unleashing the Potential: A First Look at Meta’s Next-Generation AI Chip"},"content":{"rendered":"\n

Artificial intelligences are the great technological revolution of this decade<\/a>, and the new proof of this comes from Meta<\/strong>. Mark Zuckerberg<\/strong>‘s company, which has been developing its own AIs<\/a> for some time now, has announced that it is building its first custom chip<\/strong>, created specifically to run artificial language models.<\/p>\n\n\n

\r\n
\r\n
\r\n
\r\n \"Facebook\"\r\n <\/div>\r\n
\r\n Facebook<\/span>\r\n DOWNLOAD<\/a>\r\n <\/div>\r\n
\r\n <\/path><\/path><\/text><\/svg>\r\n <\/div>\r\n <\/div>\r\n
\r\n <\/span>\r\n <\/div>\r\n
\r\n \r\n <\/div>\r\n <\/a>\r\n <\/div>\r\n<\/div>\n\n\n\n

This new chip is called MTIA<\/strong>, an acronym for Meta Training and Inference Accelerator (\u201cMeta formation and inference accelerator\u201d), and would provide a “higher computing power and efficiency” than CPUs<\/strong>, at the same time you are “customized for our internal workloads”said Santosh Janardhan<\/strong>, vice president and head of infrastructure at Meta.<\/p>\n\n\n\n

Janardhan believes that through a combination of GPUs and MTIA chips, Meta could \u201cdeliver better performance, lower latency, and higher efficiency for every workload\u201d. Of course, this new chip designed for artificial intelligence will not go on sale until 2025<\/strong>, according to TechCrunch<\/a><\/strong>, so we will have to wait a while to verify its efficiency.<\/p>\n\n\n\n

\"\"<\/figure><\/div>\n\n\n\n

But that’s not the only chip Meta is building. The company has also unveiled a new ASIC<\/a> designed for video transcoding. Dubbed MSVP<\/strong>, an acronym for Meta Scalable Video Processor, this chip could support both “the high-quality transcoding needed for VOD<\/strong> and the low latency and faster processing times required for live streaming,” Meta says in a release<\/a>.<\/p>\n\n\n

\r\n
\r\n
\r\n
\r\n \"Facebook\"\r\n <\/div>\r\n
\r\n Facebook<\/span>\r\n DOWNLOAD<\/a>\r\n <\/div>\r\n
\r\n <\/path><\/path><\/text><\/svg>\r\n <\/div>\r\n <\/div>\r\n
\r\n <\/span>\r\n <\/div>\r\n
\r\n \r\n <\/div>\r\n <\/a>\r\n <\/div>\r\n<\/div>\n\n\n\n

The chip would also help in the future to create and enhance video content for Meta’s family of apps<\/strong>, “including AI-generated content, as well as AR and VR<\/a> content in the metaverse.”<\/p>\n\n\n\n

Some of the links added in the article are part of affiliate campaigns and may represent benefits for Softonic.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"

Meta has announced the development of a chip created specifically to run AI, with greater power and computational efficiency than CPUs.<\/p>\n","protected":false},"author":9256,"featured_media":231265,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","wpcf-pageviews":0},"categories":[1015],"tags":[2353],"usertag":[],"vertical":[],"content-category":[],"class_list":["post-231262","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","tag-app-subdomain-redirectionfacebook"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/231262","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/users\/9256"}],"replies":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/comments?post=231262"}],"version-history":[{"count":1,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/231262\/revisions"}],"predecessor-version":[{"id":320155,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/231262\/revisions\/320155"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/media\/231265"}],"wp:attachment":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/media?parent=231262"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/categories?post=231262"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/tags?post=231262"},{"taxonomy":"usertag","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/usertag?post=231262"},{"taxonomy":"vertical","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/vertical?post=231262"},{"taxonomy":"content-category","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/content-category?post=231262"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}