SiMa.ai Releases Palette™ SDK 1.3: Empowering Developers with Enhanced ML Features
Are you a developer looking to streamline your machine learning (ML) application development process? Look no further than SiMa.ai’s latest release of its Palette™ SDK (version 1.3), packed with enhanced features to empower developers and optimize their ML experience.
Palette is a low-code, command-line environment specifically designed for ML application development on SiMa.ai’s Machine Learning System-on-Chip (MLSoC) silicon. With support for the entire application pipeline, from creation to deployment, developers can now easily create and deploy ML applications in minutes using Python scripting. The auto-partitioning and compilation capabilities across the MLA and Quad-core Arm Subsystem with integrated cache make the development process seamless. Additionally, developers can integrate C/C++ host applications, libraries, or functions using C/C++ APIs to achieve a cohesive production environment quickly.
With the release of Palette 1.3, SiMa.ai has enhanced its C++ APIs, making it easier to integrate the MLSoC platform into existing C++ applications. New features include acceleration pipeline status updates and enhanced error reporting, providing increased trace and debug visibility. This simplifies the porting of C++ applications using HOST + GPU/Accelerators.
Palette 1.3 also introduces int16 quantization, enhancing precision for hard-to-quantize models. This feature strikes a balance between precision and computational efficiency, making it ideal for applications with moderate memory and computational constraints. Developers can start with int8 quantization, assess accuracy using various calibration methods, and switch to int16 quantization if needed, fine-tuning calibration parameters for optimal performance.
Mr. Krishna Rangasayee, CEO and Founder of SiMa.ai, expressed his excitement about the release, stating, “At SiMa.ai, our goal is to support developers at every stage of their ML journey. We continuously add new functionalities, scripts, and models to ensure a seamless and effortless developer experience. With Palette 1.3, we are excited to further empower developers in accelerating their application pipelines at the edge.”
In addition to these enhancements, Palette 1.3 now includes MaskRCNN and YOLOv8 4-camera support over Ethernet, expanding and optimizing model support. This addition joins the more than 350 models already fully compatible with the SiMa.ai MLSoC.
SiMa.ai is a software-centric, embedded edge machine learning system-on-chip (MLSoC) company that aims to provide developers with a flexible hardware to software stack that adjusts to any framework, network, model, sensor, or modality all in one platform. Edge ML applications that run on the SiMa.ai MLSoC see a tenfold increase in performance and energy efficiency, bringing higher fidelity intelligence to ML use cases spanning various industries.
If you’re looking to innovate at the edge and unlock new paths to revenue and cost savings, SiMa.ai’s Palette 1.3 is the tool for you. With its enhanced features and optimized ML experience, developers can accelerate their application pipelines and bring their ML projects to life with ease.