{"id":100467,"date":"2026-07-09T15:27:08","date_gmt":"2026-07-09T15:27:08","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/100467\/"},"modified":"2026-07-09T15:27:08","modified_gmt":"2026-07-09T15:27:08","slug":"inference-speed-gives-cerebras-edge-in-ai-infrastructure","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/100467\/","title":{"rendered":"Inference speed gives Cerebras edge in AI infrastructure"},"content":{"rendered":"<p>The race to build the fastest AI infrastructure is reshaping the semiconductor industry, with inference speed emerging as the defining competitive dimension of the AI era.<\/p>\n<p>As <a href=\"https:\/\/siliconangle.com\/2026\/05\/13\/cerebras-stock-almost-doubles-initial-offering-price-biggest-tech-ipo-years-raised-55b\/\" rel=\"nofollow noopener\" target=\"_blank\">AI model wars intensify<\/a> across OpenAI, Anthropic and Google, the underlying compute layer is under pressure to keep pace \u2014 and the companies that moved early on inference performance are now reaping the rewards. Cerebras Systems Inc. recognized that opportunity years before the market validated it, according to <a href=\"https:\/\/www.linkedin.com\/in\/andrewdfeldman\/\" rel=\"nofollow noopener\" target=\"_blank\">Andrew Feldman<\/a> (pictured), founder and chief executive officer of Cerebras Systems.<\/p>\n<p>\u201cThe number of people who said you can\u2019t build a chip this big, it\u2019ll never work, here are the 20 reasons why it\u2019s going to fail,\u201d Feldman said. \u201cThey told us that for years, and now it works. We\u2019re the fastest inference in the industry, not by a little bit, but 10, 15, 20, 30 times faster than GPUs. And everybody wants fast results.\u201d<\/p>\n<p>Feldman spoke with theCUBE\u2019s <a href=\"https:\/\/www.linkedin.com\/in\/furrier\" rel=\"nofollow noopener\" target=\"_blank\">John Furrier<\/a> and <a href=\"https:\/\/www.linkedin.com\/in\/dvellante\" rel=\"nofollow noopener\" target=\"_blank\">Dave Vellante<\/a> at the <a href=\"https:\/\/www.thecube.net\/events\/nyse\/raise-summit-26\" rel=\"nofollow noopener\" target=\"_blank\">RAISE Summit 2026<\/a>, during an exclusive broadcast on theCUBE, SiliconANGLE Media\u2019s livestreaming studio. They discussed Cerebras\u2019s IPO milestone, the importance of inference speed, European data center buildout and the company\u2019s plans to scale manufacturing by 8x to 10x. (* Disclosure below.)<\/p>\n<p>AI inference speed and the agentic demand curve<\/p>\n<p>The case for fast inference goes well beyond user experience. As <a href=\"https:\/\/siliconangle.com\/2025\/12\/02\/exclusive-aws-ceo-matt-garman-declares-new-era-agents-new-cloud\/\" rel=\"nofollow noopener\" target=\"_blank\">agentic AI workflows proliferate<\/a>, models are making many sequential calls, reasoning over longer context windows and driving dramatically higher compute consumption \u2014 dynamics that create lasting demand advantages for Cerebras. According to Feldman, this is fundamentally changing who is buying inference and why.<\/p>\n<p>\u201cSpeed can become better answers,\u201d he said. \u201cThe longer your reasoning, the more iterations, the better answer you get. And so you can convert speed into better answers. We have a customer, AlphaSense, and they use our speed to search over more documents and that gives their customers better answers.\u201dhttps:\/\/www.youtube.com\/watch?v=LCUexLy4L3A<\/p>\n<p>Cerebras\u2019s wafer-scale architecture <a href=\"https:\/\/www.cerebras.ai\/blog\/cerebras-cs-3-vs-nvidia-dgx-b200-blackwell\" rel=\"nofollow noopener\" target=\"_blank\">sidesteps memory constraints<\/a> that slow conventional GPU systems by keeping model weights in on-chip SRAM, giving it a structural advantage as agent workloads balloon memory demand. Coding agents have been the initial beachhead, with customers including Cognition AI Inc. and OpenAI Group PBC using Cerebras in OpenAI\u2019s coding flows, Feldman noted. The company\u2019s customer base now spans financial agents through Block Inc., enterprise deployments at GlaxoSmithKline PLC and European high-performance computing centers. To support that global expansion, Cerebras plans to scale its manufacturing capacity by eight to 10 times this year.<\/p>\n<p>\u201cWe\u2019re traveling the world watching data centers be built, standing up our data centers,\u201d Feldman said. \u201cOur hardware engineers are designing next-generation chips and systems. I think it\u2019s going to be a great several years for us.\u201d<\/p>\n<p>Here\u2019s the complete video interview, part of SiliconANGLE\u2019s and theCUBE\u2019s coverage of the\u00a0<a href=\"https:\/\/www.thecube.net\/events\/nyse\/raise-summit-26\" rel=\"nofollow noopener\" target=\"_blank\">RAISE Summit 2026:<\/a><\/p>\n<p>(* Disclosure: TheCUBE is a paid media partner for the RAISE Summit event. Neither Solidigm, the headline sponsor of theCUBE\u2019s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)<\/p>\n<p>Photo: SiliconANGLE<\/p>\n<p>Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE\u2019s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.<\/p>\n<p>15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more<br \/>\n11.4k+ theCUBE alumni \u2014 Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network.<\/p>\n<p>About SiliconANGLE Media<\/p>\n<p>SiliconANGLE Media is a recognized leader in digital media innovation, uniting breakthrough technology, strategic insights and real-time audience engagement. As the parent company of <a href=\"https:\/\/cts.businesswire.com\/ct\/CT?id=smartlink&amp;url=https%3A%2F%2Fsiliconangle.com%2F&amp;esheet=54119777&amp;newsitemid=20240910506833&amp;lan=en-US&amp;anchor=SiliconANGLE&amp;index=9&amp;md5=646b1b564e2259100a2b8638aab0a552\" rel=\"nofollow noopener\" target=\"_blank\">SiliconANGLE<\/a>, <a href=\"https:\/\/cts.businesswire.com\/ct\/CT?id=smartlink&amp;url=https%3A%2F%2Fwww.thecube.net%2F&amp;esheet=54119777&amp;newsitemid=20240910506833&amp;lan=en-US&amp;anchor=theCUBE+Network&amp;index=10&amp;md5=7de2a85f95ab4a4a495cede20b8cb1da\" rel=\"nofollow noopener\" target=\"_blank\">theCUBE Network<\/a>, <a href=\"https:\/\/cts.businesswire.com\/ct\/CT?id=smartlink&amp;url=https%3A%2F%2Fthecuberesearch.com%2F&amp;esheet=54119777&amp;newsitemid=20240910506833&amp;lan=en-US&amp;anchor=theCUBE+Research&amp;index=11&amp;md5=7bb33676722925eb57d588ec343e4f6f\" rel=\"nofollow noopener\" target=\"_blank\">theCUBE Research<\/a>, <a href=\"https:\/\/cts.businesswire.com\/ct\/CT?id=smartlink&amp;url=https%3A%2F%2Fwww.cube365.net%2F&amp;esheet=54119777&amp;newsitemid=20240910506833&amp;lan=en-US&amp;anchor=CUBE365&amp;index=12&amp;md5=d310fb35919714e66ad8d42c9c0c1bc6\" rel=\"nofollow noopener\" target=\"_blank\">CUBE365<\/a>, <a href=\"https:\/\/cts.businesswire.com\/ct\/CT?id=smartlink&amp;url=https%3A%2F%2Fwww.thecubeai.com%2F&amp;esheet=54119777&amp;newsitemid=20240910506833&amp;lan=en-US&amp;anchor=theCUBE+AI&amp;index=13&amp;md5=b8b98472f8071b23ebb10ab9a8dd0683\" rel=\"nofollow noopener\" target=\"_blank\">theCUBE AI<\/a> and theCUBE SuperStudios \u2014 with flagship locations in Silicon Valley and the New York Stock Exchange \u2014 SiliconANGLE Media operates at the intersection of media, technology and AI.<\/p>\n<p>Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.<\/p>\n","protected":false},"excerpt":{"rendered":"The race to build the fastest AI infrastructure is reshaping the semiconductor industry, with inference speed emerging as&hellip;\n","protected":false},"author":2,"featured_media":100468,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[179,7493,52296,11153,396],"class_list":["post-100467","post","type-post","status-publish","format-standard","has-post-thumbnail","category-agentic-ai","tag-agentic-ai","tag-agentic-artificial-intelligence","tag-cerebras-systems-positions-inference-speed-as-the-defining-edge-in-ai-infrastructure","tag-jonathan-anthony","tag-siliconangle"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/100467","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=100467"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/100467\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/100468"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=100467"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=100467"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=100467"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}