Getting infrastructure right for generative AI
CIO
JUNE 3, 2024
The LLM work started in a London office building, which was soon outgrown by the infrastructure demands of generative AI. “It It was quite cost-effective at first to buy our own hardware, which was a four-GPU cluster,” says Doniyor Ulmasov, head of engineering at Papercup. They are much more efficient and can be more powerful.
Let's personalize your content