Qualcomm Technologies announced the launch of the Qualcomm AI software stack product portfolio to enhance Qualcomm’s leading edge in AI and intelligent networked edge. Qualcomm AI software stack is a complete set of AI solutions for OEM manufacturers and developers. It integrates various Qualcomm AI software products and has been upgraded. It can support various smart terminals through rich AI software permissions and compatibility.
JOIN US ON TELEGRAM
Moreover, Qualcomm said that this is the first time that a single AI software combination has enabled the operation of terminals across Qualcomm Technologies, covering a wide range of intelligent connected edge products, including smartphones, automobiles, XR, computing, IoT, and cloud platforms.
Qualcomm AI software stack supports different AI frameworks and mainstream runtimes including TensorFlow, PyTorch, and ONNX, as well as developer libraries and services, system software, tools, and compilers that any AI features developed for a single terminal, can be used in other AI features and easy deployment on the terminal.
Qualcomm said: “The complete Qualcomm AI software stack product portfolio is undoubtedly a huge breakthrough that will drive AI development for OEMs and developers, bringing high performance to Qualcomm Technologies’ broad product portfolio. We are pleased to use this A new product portfolio further extends the company’s unified technology roadmap and extend its leadership at the Intelligent Connected Edge.”
This complete portfolio supports direct access to Qualcomm AI Engine and the Qualcomm Cloud AI 100 dedicated AI core with Qualcomm AI Engine Direct. As part of the new solution, Qualcomm AI Engine Direct is now extensible on any AI accelerator across Qualcomm Technologies products as an AI library that can directly delegate and deploy current AI accelerators on Qualcomm Technologies platforms.
There are models, which not only provide OEMs and developers with model development functions but also support the migration of newly developed models to different products and levels. The Qualcomm AI software stack portfolio also supports a suite of tools, including the Qualcomm AI Model Enhancement Toolkit (AIMET), an AI development graphical user interface (GUI), and a model analyzer for enhanced quantification and optimization, and neural network architecture search ( NAS).
At the 2021 Snapdragon Technology Summit, Qualcomm Technologies and Google Cloud announced the integration of Google Cloud Vertex AI NAS into the Qualcomm Neural Network Processing SDK, enabling OEMs and ecosystems to create, test and deploy unique and efficient edge-side experiences.
The Qualcomm Neural Network Processing SDK remains the key to OEMs and developers running neural networks on Qualcomm Technologies products, and will therefore undergo regular upgrades and maintenance. The toolkit will provide the foundation for Qualcomm Technologies to build a unified SDK for deployment across smart connected devices.
