Qualcomm said the AI200 and AI250 chips are optimized for AI inference – the process of running already trained AI models to generate responses – rather than the training phase that requires more computing power and is dominated by Nvidia’s powerful GPUs.
Qualcomm shares rose as much as 20 percent in Monday trading on Wall Street.
The San Diego-based company is best known for its smartphone and PC processors and is entering new territory with the release.
Qualcomm said the AI200, which will be available in 2026, offers 768 gigabytes of memory per card and uses direct liquid cooling to manage heat in tightly packed server racks that each consume up to 160 kilowatts.
The company said the AI250, expected in 2027, would be ten times more effective in terms of memory bandwidth than current products on the market while consuming less power. Nvidia, the epitome of the generative AI boom, currently dominates the AI chip market, powered by its H100 and newer H200 GPU accelerators used in training and running AI models in massive, purpose-built data centers. AMD, the second largest player, is gaining ground and positioning itself as a challenger to Nvidia’s dominance.
Both companies recently entered into agreements with OpenAI, the maker of ChatGPT, as the industry tries to ramp up the massive infrastructure needed to support the AI frenzy.
This has raised fears that Wall Street could be in the grip of an AI stock bubble reminiscent of the Internet boom and bust of the late 1990s and 2000s.
Yet companies are largely rewarded for their connection to the AI bonanza. Shares of AMD rose 35 percent on the day of the announcement, while OpenAI, the world’s most valuable private company, is valued at $500 billion.
#Qualcomm #shares #rise #launch #chip