Microsoft revealed a new chip intended for use in artificial intelligence (AI) applications in a news article published on November 15.
The company said it unveiled the chip, dubbed Azure Maia 100 AI Accelerator, at its Microsoft Ignite conference the same day. The Maia 100 chip is optimized for use in artificial intelligence applications, including generative AI.
Microsoft’s blog also cited Sam Altman, CEO of OpenAI, who said his company, best known for ChatGPT, helped design the chip. Altman said:
“Since our first partnership with Microsoft, we have collaborated to co-design Azure’s AI infrastructure at every layer… We were excited when Microsoft first shared its designs for the Maia chip, and we have worked together to refine it and test it with our models. .”
Altman added that Azure’s architecture is “now optimized down to silicon with Maia.” He said the improvement would lead to better AI models and more affordable access. OpenAI has also suspended paid subscriptions due to high demand.
In a separate interview with CNBC, Rani Borkar, Microsoft’s vice president for Azure Hardware Systems, said Microsoft is currently testing how the Maia 100 works with its Bing AI chatbot and GitHub Copilot coding assistant. It also tests the chip’s ability to power OpenAI’s GPT-3.5 Turbo Large Language Model (LLM).
Microsoft simultaneously announced the Azure Cobalt CPU Cobalt 100 Arm chip, aimed at general cloud computing. The company said both chips would be introduced in its own data centers in early 2024.
Besides Microsoft, several other industry heavyweights are also making progress in the development of AI chips. Nvidia is currently leading the way with its H100 Tensor Core GPU chips, widely used in the AI industry.
In fact, Microsoft said in today’s blog post that it is expanding its industry partnerships to provide customers with access to Nvidia’s H100 chips and its upcoming H200 chips. CNBC, meanwhile, suggested that Maia would compete with the H100 chip.
A shortage of Nvidia chips in the market presents a significant opportunity for other technology companies to bolster their chip production. Reports from October indicated that OpenAI could begin producing chips in-house. Meta announced details of its next generation of AI chips in May. Google announced a chip in August called Cloud TPUv5e for use in AI.