Qualcomm Technologies has announced it is collaborating with Meta to optimize the on-device execution of Meta's Llama 2 large language models without relying on cloud services alone. The ability to execute generative AI models such as Llama 2 on devices like smartphones, PCs, VR/AR headsets, and vehicles allows developers to save on cloud costs and provide users with more private, more reliable, and personalized experiences.
Qualcomm plans to offer on-device Llama 2-based AI implementations to facilitate the development of innovative AI applications. Customers, partners, and developers will be able to create use cases such as intelligent virtual assistants, productivity applications, content creation tools, and more. These new on-device AI experiences, powered by Snapdragon, can function in areas with no connectivity or even during flight.
Meta and Qualcomm have a long history of collaborating to advance technology and provide the next generation of premium device experiences. The companies' current efforts to support the Llama ecosystem involve both research and product engineering. Qualcomm indicated it is uniquely positioned to support the Llama ecosystem due to its leadership in on-device AI.
Qualcomm claimed that the company has an unparalleled footprint at the edge, with billions of smartphones, vehicles, XR headsets and glasses, PCs, IoT, and other devices powered by its industry-leading AI hardware and software solutions, allowing for the scalability of generative AI.
Qualcomm is scheduled to make available Llama 2-based AI implementation on devices powered by Snapdragon starting from 2024 onwards, according to the company.
"We applaud Meta's approach to open and responsible AI and are committed to driving innovation and reducing barriers-to-entry for developers of any size by bringing generative AI on-device," said Durga Malladi, senior VP and GM of technology, planning and edge solutions businesses for Qualcomm Technologies. "To effectively scale generative AI into the mainstream, AI will need to run on both the cloud and devices at the edge, such as smartphones, laptops, vehicles, and IoT devices."
