| Mobile Web

Nvidia to unveil first dedicated inference chip as AI inference chip rivalry intensifies

Nvidia is preparing to launch a dedicated inference chip designed to speed up AI responses, with CEO Jensen Huang (젠슨 황) expected to unveil it at the GTC developer conference starting on March 16, the Financial Times reported. The chip is the first product since Nvidia hired Groq founders in a $20 billion deal in December. Nvidia plans to add an LPU line alongside its Vera Rubin GPUs and use SRAM instead of HBM.