Qualcomm Technologies Inc. and Meta are working together to optimize the on-device execution of Meta’s Llama 2 large language models, eliminating dependency on cloud services. This allows generative AI models such as Llama 2 to run directly on devices such as smartphones, PCs, VR/AR headsets and vehicles. By doing so, developers can reduce cloud costs while providing users with personalized, reliable, and personalized experiences.
In line with this initiative, Qualcomm Technologies is committed to offering Llama 2-based AI implementations on the device, opening up opportunities for the development of innovative AI applications. Customers, partners and developers can use this technology to create intelligent virtual assistants, productivity tools, content creation applications, entertainment and more. Powered by Snapdragon®, these new on-device AI experiences can function even without connectivity, making them suitable for areas with limited or no internet access, including airplane mode.
Qualcomm and Meta: AI on the device with Llama 2
“We applaud Meta’s approach to open and accountable AI and are committed to driving innovation and reducing barriers to entry for developers of all sizes by bringing generative AI to the device,” said Durga Malladi, senior vice president and general manager of technology, planning and edge solutions companies, Qualcomm Technologies, Inc. “To effectively scale generative AI into the mainstream, AI will need to run on the cloud as well as on devices at the edge, such as smartphones, laptops, vehicles and IoT devices.”
Meta and Qualcomm Technologies have a long history of working together to drive technological advancements and deliver cutting-edge device experiences. Currently, their joint efforts to support the Llama ecosystem include research and product development efforts. Qualcomm Technologies’ prominent position in on-device AI is uniquely positioned to contribute to the success of the Llama ecosystem. The company boasts an extensive edge footprint, with billions of devices such as smartphones, vehicles, XR headsets, glasses, PCs, IoT devices and more, powered by leading AI hardware and software solutions, creating tremendous potential for the scalability of generative AI.
Starting in 2024, Qualcomm Technologies plans to introduce Llama 2-based AI implementations on Snapdragon-powered devices. To help developers optimize applications for on-device AI, they can leverage the Qualcomm AI Stack, an exclusive set of tools designed to more efficiently process AI on Snapdragon. This capability makes on-device AI feasible even on small, slim and lightweight devices. To stay on top of the latest updates, developers can subscribe to Qualcomm Technologies’ monthly newsletter.
