The company has also announced the introduction of its Hailo-10 high-performance generative AI (GenAI) accelerators allowing users to both own and run GenAI applications locally without registering to cloud-based GenAI services.
The new funding round was led by current and new investors including the Zisapel family, Gil Agmon, Delek Motors, Alfred Akirov, DCLBA, Vasuki, OurCrowd, Talcar, Comasco, Automotive Equipment (AEV), and Poalim Equity. To date the company has raised more than $340 million.
“The closing of our new funding round enables us to leverage all the exciting opportunities in our pipeline, while setting the stage for our long-term future growth. Together with the introduction of our Hailo-10 GenAI accelerator, it strategically positions us to bring classic and generative AI to edge devices in ways that will significantly expand the reach and impact of this remarkable new technology,” said Hailo CEO and Co-Founder Orr Danon.
“We designed Hailo-10 to seamlessly integrate GenAI capabilities into users’ daily lives, freeing users from cloud network constraints. This empowers them to utilise chatbots, copilots, and other emerging content generation tools with unparalleled flexibility and immediacy, enhancing productivity and enriching lives,” added Danon.
The Hailo-10 GenAI accelerator enables a wide range of applications and leverages the same comprehensive software suite currently used across the Hailo-8 AI accelerators and the Hailo-15 AI vision processors, enabling seamless integration of AI capabilities across multiple edge devices and platforms.
Enabling GenAI at the edge ensures continuous access to GenAI services, regardless of network connectivity; obviates network latency concerns, which can otherwise impact GenAI performance; promotes privacy by keeping personal information anonymised and enhances sustainability by reducing reliance on the substantial processing power of cloud data centres.
“As GenAI on the edge becomes immersive, the focus turns to handling large LLMs in the smallest possible power envelope, essentially less than five watts,” explained Danon.
Among popular GenAI platforms, Hailo-10 can run Llama2-7B with up to 10 tokens per second (TPS) at under 5W of power. In processing Stable Diffusion 2.1, a popular model that produces images from text prompts, Hailo-10 is rated at under 5 seconds per image in the same ultra-low power envelope.
Hailo-10 is said to be capable of up to 40 TOPS (tera operations per second), a new performance standard for edge AI accelerators. The company also claims that the Hailo-10 is faster and more energy efficient than integrated neural processing unit (NPU) solutions and delivers at least 2X more performance at half the power of Intel’s Core Ultra NPU, according to recently published benchmarks.
Early applications of Hailo-10 GenAI accelerators will be targeting PCs and automotive infotainment systems. Hailo will begin shipping samples of the Hailo-10 GenAI accelerator in Q2 of 2024.
“Whether users employ GenAI to automate real-time translation or summarization services, generate software code, or images and videos from text prompts, Hailo-10 lets them do it directly on their PCs or other edge systems, without straining the CPU or draining the battery,” Danon concluded.
