Seoul, Korea, and San Jose, CA – May 15, 2024 – AiM Future, a leading provider of concurrent multimodal inference accelerators for edge and endpoint devices, has just announced the launch of its next-generation Generative AI Architecture, “GAIA,” and Synabro software development kit. These GAIA-based accelerators are designed to enable energy-efficient transformers and large language models (LLMs) on resource-constrained devices while supporting valuable investment in existing convolutional and recurring neural networks. With the Synabro SDK, developers can enjoy a unified development flow to optimize pre-trained models for execution on GAIA-based devices. The combined solution offers a highly flexible general-purpose neural processing engine that is scalable from smart sensors to edge-of-network infrastructure applications.
Built on many years of developing new technologies for smart home devices, GAIA’s unique memory, neural engine, and internal communication architecture boasts high utilization further increasing efficiency within an already ultra-low energy envelope. Enabling users to mix and scale neural engines, CPU architectures and core counts with an elastic memory structure opens the addressable application space for mission-critical, real-time edge applications from tens of giga operations (GOPS) to hundreds of trillions of operations per second (TOPS). The Synabro SDK allows developers to migrate pre-trained models to GAIA-based hardware quickly and intuitively. Furthermore, advanced quantization, pruning, and sparsity techniques enable users to extend the Pareto curve by optimizing for accuracy, latency, and memory size.
“The AiM Future team has dedicated years to tackling intricate consumer electronics demands while also studying the automotive and industrial sectors,” stated CEO ChangSoo Kim. “We have closely listened to our customers and have developed cutting-edge technology to maintain our position at the forefront of this rapidly evolving market.”
AiM Future is currently licensing GAIA and Synabro to strategic lead partners, with general availability expected in Q4, 2024. Interested parties can visit AiM Future at the Embedded Vision Summit, which will be held on May 21-23 at the Santa Clara Convention Center.
About AiM Future
The company, headquartered in Seoul, South Korea, was established in 2021 with LG Electronics as a strategic investor. Later, it received a Series-A round investment from top venture capital firms such as L&S Venture Capital, Hi Investment Partners, Daedeok Venture Partners, KB Investment, and We Ventures. The company specializes in developing neural network hardware accelerator IP and complementary software. Its flagship NeuroMosAIc architecture was successfully commercialized in 2019, and the company has entered into several license agreements with partners across the globe.
© Edge AI and Vision Alliance
