Technology

FuriosaAI Partners with Broadcom to Build Next-generation Inference Platform for the Agentic Era

MOUNTAIN VIEW, Calif., May 27, 2026--FuriosaAI, a builder of high-performance inference silicon, today announced a strategic partnership with Broadcom (NASDAQ: AVGO) to develop its third-generation AI accelerator. This collaboration evolves Furiosa’s Tensor Contraction Processor (TCP) architecture into a scale-up inference platform engineered for serving frontier agentic systems at massive scale of global hyperscale environment.

articleBroadcom Inc.May 27, 20264/company/broadcom-inc/news/furiosaai-partners-with-broadcom-to-build-next-generation-inference-platform-for-the-agentic-era
FuriosaAI Partners with Broadcom to Build Next-generation Inference Platform for the Agentic Era

About this update from Broadcom Inc.

[{"type":"image","alt":"","displaySize":"","headline":null,"caption":"","credit":null,"className":"","disableSlideshowImg":false,"size":{"original":{"width":2400,"height":624,"url":"https://media.zenfs.com/en/business-wire.com/0503de236fe9d617f436007ccd851ebc"},"resized":{"url":"https://s.yimg.com/ny/api/res/1.2/uICOqIfuFR6I5g8GYuTTcw--/YXBwaWQ9aGlnaGxhbmRlcjt3PTk2MDtoPTI1MA--/https://media.zenfs.com/en/business-wire.com/0503de236fe9d617f436007ccd851ebc","width":960,"height":250},"resize_sm":{"url":"https://s.yimg.com/ny/api/res/1.2/UIxoJlReg1684G8CjTl.xA--/YXBwaWQ9aGlnaGxhbmRlcjt3PTY0MDtoPTE2Ng--/https://media.zenfs.com/en/business-wire.com/0503de236fe9d617f436007ccd851ebc","width":640,"height":166},"lightbox":{"url":"https://s.yimg.com/ny/api/res/1.2/SaeDq5Q0M.vBbnQj8k3Kng--/YXBwaWQ9aGlnaGxhbmRlcjt3PTI0MDA7aD02MjQ-/https://media.zenfs.com/en/business-wire.com/0503de236fe9d617f436007ccd851ebc","width":1200,"height":312}},"lazy":false},{"type":"text","content":"MOUNTAIN VIEW, Calif., May 27, 2026--(BUSINESS WIRE)--FuriosaAI, a builder of high-performance inference silicon, today announced a strategic partnership with Broadcom (NASDAQ: AVGO) to develop its third-generation AI accelerator. This collaboration evolves Furiosa’s Tensor Contraction Processor (TCP) architecture into a scale-up inference platform engineered for serving frontier agentic systems at massive scale of global hyperscale environment.","length":449,"tagName":"p"},{"type":"text","content":"Moving beyond a traditional ASIC partnership, Furiosa and Broadcom are combining FuriosaAI's AI architecture and software stack with Broadcom's leadership in scale-up AI networking solutions to build a rack-scale inference platform.","length":240,"tagName":"p"},{"type":"text","content":"RNGD: A proven foundation for production inference","length":50,"tagName":"p"},{"type":"text","content":"The partnership builds on the commercial maturity of RNGD, FuriosaAI’s data center inference chip. Currently in mass production and fabricated at TSMC’s 5nm advanced process, RNGD is a 180W, PCIe-based accelerator designed for high-performance LLM and agentic AI workloads.","length":273,"tagName":"p"},{"type":"text","content":"RNGD has been validated in production environments by global leaders including Samsung SDS and LG AI Research, proving the efficiency of the TCP architecture. By providing high throughpu...

More updates from Broadcom Inc.

BroadcomRNGDFuriosa CofounderTensor Contractionmass productionFuriosainferencesoftware stackarchitecture