US chipmaker Nvidia is preparing to launch a new processor aimed at accelerating artificial intelligence performance for clients including OpenAI, according to a media report published Friday.
Lamine Yamal Nets First Career Hat-Trick as Barcelona Beat Villarreal 4-1 to Extend La Liga Lead
The upcoming platform is being developed specifically for “inference” computing — the process that enables AI models to generate responses to user queries quickly and efficiently. The new system is expected to be unveiled at Nvidia’s annual GTC developer conference in San Jose next month.
The report said the platform will incorporate a chip designed by AI hardware startup Groq, signaling closer collaboration between established chipmakers and emerging AI firms. Reuters said it could not independently verify the claims, and both Nvidia and OpenAI declined immediate comment.
Earlier reports indicated that OpenAI has expressed concerns about the speed of existing Nvidia hardware when handling certain workloads, particularly software development tasks and AI systems communicating directly with other applications. Sources suggested OpenAI is seeking specialized hardware capable of handling a portion of its growing inference computing demands.
The ChatGPT developer has also explored partnerships with companies such as Cerebras Systems and Groq to improve performance. However, Nvidia reportedly secured a $20-billion licensing agreement with Groq, effectively ending OpenAI’s separate negotiations.
In a separate development last year, Nvidia announced plans to invest up to $100 billion in OpenAI, gaining a stake in the company while helping finance large-scale purchases of advanced AI chips needed to expand computing capacity.
