New Unified Qualcomm AI Stack Portfolio Revolutionizes Developer Access and Expands AI Leadership
Qualcomm Technologies, Inc. announced the Qualcomm® AI Stack portfolio, accelerating the company’s leadership in artificial intelligence (AI) and Connected Intelligent Edge. Combining and enhancing its best AI software offerings, Qualcomm AI Stack is a comprehensive AI solution for OEMs and developers, supporting a wide range of smart devices with broad AI software access and compatibility . For the first time, a single portfolio of AI software runs on devices powered by Qualcomm Technologies, spanning the wide range of Connected Intelligent Edge products – including mobile, automotive, XR, computing, IoT and cloud platforms.
Qualcomm AI Stack supports various popular AI frameworks and runtimes including TensorFlow, PyTorch and ONNX, libraries and developer services, system software, tools and compilers so that any AI functionality developed for a device can easily be deployed to others.
“This comprehensive Qualcomm AI Stack portfolio is a truly revolutionary step in improving AI development for OEMs and developers and achieving high performance across our entire product portfolio,” Ziad said. Asghar, Vice President of Product Management, Qualcomm Technologies, Inc. “We are excited to extend our unique technology roadmap with this new portfolio and extend our leadership in the Connected Intelligent Edge.
This comprehensive portfolio provides direct access to the Qualcomm® AI Engine and dedicated AI cores on Qualcomm® Cloud AI 100 using Qualcomm® AI Engine direct. As part of the new offering, the direct Qualcomm AI Engine will now accommodate all AI accelerators within a full line of Qualcomm Technologies products. Qualcomm AI Engine direct is an AI library that delegates and deploys existing models directly to AI accelerators on Qualcomm Technologies platforms and will now provide OEMs and developers the ability to develop a feature and then move the same model on different products and levels.
“Qualcomm Technologies continues to deliver advanced AI solutions that make it easier for developers to harness today’s most powerful AI and ML capabilities,” said Yuan Yu, Distinguished Engineer for Architecture AI executives at Microsoft. “We are excited to bring Qualcomm AI Software technologies to developers across our ecosystems, including the Qualcomm Neural Processing SDK for Windows, to deliver edge-to-cloud AI capabilities by delivering unified AI software. and comprehensive that scales from clients to servers.
The Qualcomm AI Stack portfolio will also include a suite of tools including Qualcomm® AI Model Efficiency Toolkit (AIMET), an AI development graphical user interface (GUI), model analyzers to drive improved quantification and optimization, and Neural Architecture Search (NAS). As announced at Snapdragon Tech Summit 2021, Qualcomm Technologies and Google Cloud have integrated the Google Cloud Vertex AI NAS, which enables OEMs and the ecosystem to build, test and deploy unique and efficient experiences at the edge. Qualcomm’s Neural Processing SDK remains a key product for OEMs and developers to run their neural networks on a wide range of Qualcomm Technologies products and will continue to receive regular updates and support. This collective will give Qualcomm Technologies a baseline to create domain-specific SDKs to deploy on the Connected Intelligent Edge.