Rebellions develops AI accelerators that utilize HBM3e chiplet architecture and 5nm System-on-Chip technology to enhance energy efficiency and computational performance for deep learning applications. The company addresses the need for scalable and efficient AI inference solutions in the rapidly growing generative AI market.
Funding
$224.7M 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.
KC+1Founders
Product
Problem
The increasing demand for generative AI applications requires scalable and energy-efficient AI inference solutions that can handle complex deep learning models. Existing solutions often struggle to provide the necessary computational performance without consuming excessive power, hindering widespread deployment.
Solution
Rebellions offers high-performance AI inference accelerators designed to address the computational and energy efficiency challenges of generative AI. Their solutions leverage HBM3e chiplet architecture and 5nm System-on-Chip (SoC) technology to deliver exceptional performance. The company's flagship products, REBEL and ATOM™, are designed for hyperscale workloads and versatile inference applications, respectively. Rebellions' modular framework enables scalable deployments, allowing customers to start lean and scale green.
Target Audience
The primary target audience includes organizations deploying generative AI applications at scale, such as hyperscale data centers, cloud service providers, and enterprises developing AI-powered products.
Features
- HBM3e chiplet-based architecture for high memory bandwidth and compute density (REBEL)
- 5nm Versatile Inference SoC for energy-efficient AI processing (ATOM™)
- Support for popular deep learning models including Pytorch, HuggingFace, SDXL-turbo, Llama3, Llama2, Mistral-7B, Gemma, and Phi3
- Software Development Kit (SDK) for developers to optimize and deploy models
- Modular framework for scalable POD (Point of Delivery) deployments