Qualcomm Launches IMSDK 2.0 to Accelerate Edge AI Development

Dynamic View Beating AI News: Qualcomm has launched the Qualcomm Intelligent Multimedia SDK (IMSDK) 2.0, introducing a unified AI and multimedia development framework for Qualcomm Dragonwing and Linux edge platforms designed to simplify integration of features such as cameras, audio/video, sensors, AI inference, and cloud connectivity, accelerating the deployment of smart cameras, robots, drones, and industrial AI products. IMSDK 2.0 adds Python and C++ Pipeline APIs and application builders, generative AI inference, containerized microservices, AI programming agent capabilities, and “documentation as code” functionality. Developers can now switch AI models without rebuilding the entire multimedia pipeline, using multiple inference runtimes such as QAIRT, ONNX Runtime, and TFLite. Qualcomm states that IMSDK 2.0 is built on the GStreamer architecture and integrates hardware-accelerated plugins, zero-copy data transfer, and multi-stream, multi-model pipeline capabilities to support applications including visual AI, LLM/VLM, audio AI, and text-to-image generation. Its containerized microservices cover inference, analytics, and platform services, and support enterprise-grade connectivity via Kafka, MQTT, AWS IoT, and Azure IoT. Additionally, IMSDK 2.0 introduces AI programming agent capabilities that assist developers with pipeline configuration, model integration, compilation, debugging, and deployment through natural language. Qualcomm notes that this SDK is already being used by companies such as Samsung, Amazon, and Bose for product development.