Qualcomm AI Stack portfolio has been released. Qualcomm AI Stack is a comprehensive artificial intelligence (AI) solution for OEMs and developers, providing a wide range of intelligent devices with broad access to and interoperability with AI software. It does this by combining and improving its best-in-class AI software offerings.
Listen to this story
This new unified AI software portfolio is compatible with a wide range of Qualcomm Technologies-powered devices, including mobile, automotive, XR, computing, IoT, and cloud platforms.
To make it simple to deploy any AI feature on any device, Qualcomm AI Stack supports a variety of AI frameworks and well-known runtimes, including TensorFlow, PyTorch, and ONNX, developer libraries and services, system software, tools, and compilers.
“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 product portfolio,” said Ziad Asghar, Vice President of Product Management at Qualcomm Technologies. “We’re delighted to extend our one technology roadmap with this new portfolio and expand our leadership in the Connected Intelligent Edge.”
With Qualcomm AI Engine direct, this extensive portfolio offers direct access to the Qualcomm AI Engine and dedicated AI cores on Qualcomm Cloud AI 100. The Qualcomm AI Engine direct will now grow across every AI accelerator inside a wide array of Qualcomm Technologies devices as part of the new offering.
Qualcomm AI Engine direct is an AI library that delegates and deploys existing models directly to the AI accelerators on Qualcomm Technologies platforms and will now provide OEMs and developers the ability to develop one feature, then move the same model across different products and tiers.
“Qualcomm Technologies continues to deliver advanced AI solutions that make it easier for developers to leverage today’s most powerful AI and ML capabilities,” said Yuan Yu, Distinguished Engineer for AI Frameworks Architecture at Microsoft. “We’re enthusiastic to bring Qualcomm AI Software technologies to developers in our ecosystems, including the Qualcomm Neural Processing SDK for Windows, to offer edge-to-cloud AI capabilities by providing unified, comprehensive AI software that scales from clients to servers.”
Along with a variety of tools, the Qualcomm AI Stack portfolio will also feature the Qualcomm AI Model Efficiency Toolkit (AIMET), an AI development GUI, model analyzers to promote improved quantization and optimization, and Neural Architecture Search (NAS). Qualcomm Technologies and Google Cloud integrated Google Cloud Vertex AI NAS, which lets OEMs and the ecosystem to develop, test, and roll out distinctive and effective experiences on the edge, as unveiled at Snapdragon Tech Summit 2021. Qualcomm AI Stack is commercially available now.
Qualcomm AI Engine direct is an AI library that delegates and deploys existing models directly to the AI accelerators on Qualcomm Technologies platforms
The Qualcomm AI Stack portfolio will also feature the Qualcomm AI Model Efficiency Toolkit (AIMET), an AI development GUI, model analyzers to promote improved quantization and optimization, and Neural Architecture Search (NAS).