By using Neuchips’ Viper series cards, the collaboration also offers power efficiency and offline LLM to provide businesses with maximum privacy and security.
Neuchips , a leading provider of artificial intelligence (AI) application-specific integrated circuits (ASICs), announces a collaboration with Vecow and ShareGuru of Golden Smart Home (GSH) Technology Corp. The partnership aims to revolutionize SQL data processing through a private, secure, and power-efficient AI solution that delivers real-time insights from internal databases via natural language queries.
“Our collaboration with Vecow and GSH represents the future of industrial AI deployment,” said Ken Lau , CEO of Neuchips. “At Embedded World 2025, visitors to the Vecow booth will be able to see how the unique capabilities of our Viper AI accelerator card—including support for 12B parameter models with power consumption as low as 45W—complement Vecow’s robust industrial edge AI computing systems and GSH’s ShareGuru SLM solutions. This powerful combination delivers proprietary, data-efficient and secure AI processing that meets the demanding requirements of modern industrial environments. We are proud to partner with Vecow to bring this generative AI innovation to the enterprise-focused application space.”
“As local generative AI applications expand, the demand for multimodal large language models (LLMs) is growing rapidly,” said Joseph Huang , Executive Vice President of Vecow. “As a leading edge AI computing solution service provider, Vecow is partnering with Neuchips to develop cutting-edge RAG-based LLM solutions, allowing users to access the latest data without training models, delivering more relevant and high-quality results. It is essential for our customers looking for a cost-effective, compact, and power-efficient AI workstation that outperforms traditional cloud-based GPU solutions.”
Combining forces to achieve the ultimate AI-powered data processing solution
As database complexity increases and SQL skills remain scarce, businesses face significant delays in extracting critical insights from data. However, online AI models cannot be used due to the lack of protection of sensitive information.
To solve these problems for businesses across all industries, the innovative solution leverages the Vecow ECX-3100 RAG Edge AI inference workstation, a RAG (Recovery-Augmented Generation)-enabled LLM computing platform. It runs GSH’s ShareGuru QA 2.0 solution, powered by the ShareGuru SLM platform, using a single Neuchips LLM card – the Viper Series Gen AI card.
Also Read: IonQ & GDIT Partner to Develop Quantum Solutions in U.S.
Overall, the solution enables the use of human language to generate SQL queries, making them more accessible and efficient, while reducing the costs of SQL expertise. It also offers:
- Maximum data privacy and security : Neuchips offline card runs the ShareGuru solution and platform locally
- High accuracy : by validating power queries with AI
- High energy efficiency : Neuchips Viper series offers 45W energy efficiency with a full 12 billion parameter model
Neuchips Viper Series AI Accelerator Card
Launched at COMPUTEX 2024, the Viper series offloads over 90% of the resources required for generative AI from the CPU to unleash the full potential of LLMs. It stands out in the market by offering:
- Additional memory capacity of 32 GB
- Native support for BF16 structured language model
- Neuchips’ Raptor Gen AI accelerator chip unveiled at CES 2024
Looking ahead to 2026, Neuchips plans to focus on low-power, multi-mode ASICs to achieve further performance gains.
Source: PRNewswire
