SambaNova Systems, a provider of integrated AI platforms, has unveiled its new chip, the SN40L, which will power its full-stack large language model (LLM) platform, the SambaNova Suite. The SN40L chip is manufactured by TSMC.
The SN40L supports dense and sparse computing capabilities and addresses High Bandwidth Memory (HBM) and DRAM from a single chip, enabling AI algorithms to choose the most appropriate memory for a given task.
The chip can handle models with five trillion parameters and enables developers to design high-quality LLM models, enabling faster inference and training while lowering overall costs of ownership.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.