Home > Business > Industry

Samsung produces Groq's AI chips as Nvidia bets big on inference

Published: 17 Mar. 2026, 08:39 Updated: 17 Mar. 2026, 10:52

LEE JAE-LIM
[email protected]

Nvidia CEO Jensen Huang speaks during an Nvidia conference focusing on AI in San Jose, California, on March 16. [AP/YONHAP]

Samsung Electronics is manufacturing the latest processors from U.S. AI chip startup Groq, with first shipments expected to begin in the third quarter of this year, Nvidia CEO Jensen Huang said Monday.

Speaking at the keynote of Nvidia’s GTC 2026 in San Jose, California, Huang thanked Samsung for producing Groq’s latest inference chip, the Nvidia Groq 3 LPU, and said the Korean chipmaker is accelerating production.

“I want to thank Samsung, who manufactures the Groq 3 LPU chip for us, and they’re cranking as hard as they can,” he said.

LPU refers to language processing units designed for AI inference. Huang added that the chip is already in production and is expected to begin shipping in the second half of the year, likely around the third quarter.

Although rumors had circulated for months, this marked the first time Huang publicly confirmed that Samsung’s foundry business is manufacturing Groq’s newest AI chip. Huang also said the inference accelerator rack, the Nvidia Groq 3 LPX that is powered by 256 Groq 3 LPUs, can speed up inference workloads by as much as 35 times when paired with the Vera Rubin architecture.

Nvidia invested $20 billion in the U.S. startup in December 2025 to license Groq’s inference technology and recruit talent from the company.

BY LEE JAE-LIM [[email protected]]