Eta Compute develops a no-code MLOps toolchain that optimizes machine learning models for low-power edge devices, enhancing their efficiency and accuracy. This technology enables enterprises to effectively monitor resources while minimizing energy consumption and inference time.
Funding
$33.4M 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 machine learning models to low-power edge devices is challenging due to resource constraints, requiring specialized expertise in both machine learning and embedded systems. Optimizing models for size, speed, and energy efficiency often involves manual tuning and deep knowledge of specific chip architectures.
Solution
Eta Compute's Aptos is a no-code MLOps toolchain designed to streamline the development, deployment, and management of machine learning models on low-power edge devices. The platform optimizes models to reduce their size, decrease inference time, and conserve energy, while maintaining high accuracy. Aptos bridges the gap between AI and embedded systems by eliminating the need for developers to understand the intricacies of specific chip capabilities and constraints.
Target Audience
The primary users are machine learning developers and embedded systems engineers who need to deploy efficient and accurate ML models on low-power edge devices.
Features
- No-code interface for model development, deployment, and management
- Model optimization techniques tailored for low-power edge processors
- Automated reduction of model size, inference time, and energy consumption
- Support for various edge ML applications
- Streamlined workflow for both ML developers and embedded systems engineers