Qualcomm Launches IMSDK 2.0 to Drive Edge AI Application Development

Qualcomm has released the Qualcomm Intelligent Multimedia SDK (IMSDK) 2.0, aimed at Qualcomm Dragonwing and Linux edge platforms. This new version introduces a unified AI and multimedia development framework that simplifies the integration of features such as camera, audio and 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, an application builder, generative AI inference, containerized microservices, AI programming agent capabilities, and a "documentation-as-code" feature. Developers can switch AI models using inference runtimes like QAIRT, ONNX Runtime, and TFLite without restructuring the entire multimedia pipeline. IMSDK 2.0 is based on the GStreamer architecture and combines hardware acceleration plugins, zero-copy data transfer, and multi-stream, multi-model pipeline capabilities to support visual AI, LLM/VLM, audio AI, and text-to-image applications. Its containerized microservices cover inference, analytics, and platform services, supporting enterprise-level connections such as Kafka, MQTT, AWS IoT, and Azure IoT. IMSDK 2.0 introduces AI programming agent skills that assist developers in configuring pipelines, integrating models, compiling, debugging, and deploying through natural language. This SDK has already been utilized by companies like Samsung, Amazon, and Bose for related product development.