Small AI Chip Makers Eye Gains in Inference Workloads
SMRTR summary
SambaNova's new cloud service, powered by their SN40L AI chip, offers speedy inferencing for Meta's Llama 3.1 models, processing up to 580 tokens per second, aiming to rival NVIDIA in the booming AI chip market.
SMRTR provides this summary for quick context. The original article belongs to Daily.dev.
Read the original article