CoCoPIE develops a full-stack optimization toolchain that enhances AI model performance on edge devices by reducing model size, improving accuracy, and increasing processing speed. This technology enables efficient AI deployment on mobile and IoT platforms, minimizing server reliance and enhancing data privacy.
Funding
$10.6M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Deploying AI models on edge devices is challenging due to resource constraints, including limited processing power, memory, and battery life. Optimizing models for size, speed, and accuracy often requires specialized expertise and manual tuning, increasing development time and costs.
Solution
CoCoPIE offers a full-stack optimization toolchain designed to streamline AI deployment and execution on edge devices, such as mobile phones and IoT devices. The toolchain, called XGen, simultaneously optimizes AI model size, accuracy, and processing speed through model-code co-optimization. This enables efficient AI performance on resource-constrained devices, reducing reliance on servers and enhancing data privacy by allowing AI tasks to run locally. CoCoPIE also provides pre-optimized AI modules (XStore) that can be readily integrated into applications by developers without specialized AI expertise.
Target Audience
CoCoPIE targets AI developers seeking to optimize models for edge deployment, app developers looking for pre-optimized AI modules, and chip companies/OEMs with custom AI needs.
Features
- XGen: Full-stack toolchain for optimizing AI model size, accuracy, and speed
- Model-code co-optimization for efficient performance on edge devices
- XStore: Pre-optimized AI modules for various domains, ready for integration into applications
- Automatic software solution that boosts the performance of existing hardware
- Enables AI to run directly on end devices, reducing server costs
- Facilitates privacy-friendly solutions by processing data locally on devices