
What happened
Navitas Semiconductor announced a strategic collaboration with Nvidia to develop a 24-kilowatt power delivery board for AI data centers, and its shares climbed 5% in after-hours trading.
Why it matters
The partnership expands Navitas' portfolio of AI data-center power solutions co-developed with Nvidia, potentially strengthening its position in this supply chain.
Summaries like this, in your inbox every morning.
Navitas' latest collaboration with Nvidia builds on a previously announced 20 kW board also co-developed with Nvidia. The new 24 kW board expands Navitas' portfolio of 800 VDC AI data-center power solutions, suggesting an ongoing partnership relationship rather than a one-off project. Engineered to fit Nvidia's 400 mm × 60 mm form factor, the board targets 97% efficiency at full load with a power density exceeding 2,000 W/in³. It utilizes 16 of Navitas' NV6034 GaNFast FETs on the primary side, configured in a stacked half-bridge topology with the company's dual-cooled DFN 8 × 8 packaging to optimize thermal management. The compact design allows it to be integrated directly onto the compute motherboard adjacent to the xPUs, routing 12 V directly to the voltage regulator module to minimize power-delivery losses and simplify overall complexity. The announcement came alongside other news items such as FormFactor's $300M investment deal with Teradyne and a mixed market session ahead of bank earnings and CPI data.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
At Fortune's AIQ Summit at the New York Stock Exchange, executives from ServiceNow, HPE, Palo Alto Networks, B…

Nerf Bench, described on the Bridgebench blog, scores a model's Power from performance, tokens used and cost…

Cisco and Nvidia are partnering on a new generation of optical networking technology designed for the explodin…

Honeyjar, a startup led by CEO Michelle Masek and CCO Nadia Jamshidi, is building AI that automates communicat…

Meta's Superintelligence Lab released Muse Wonder and Muse Wonder Full, its first frontier models; Meta's test…

Microsoft will deploy its Azure Maia AI chips at multi-gigawatt scale starting in 2027, making them the compan…
