Continuum AI is now publicly available. Try out the first confidential LLM platform!

Continuum blog post image


Continuum: The first confidential LLM platform to revolutionize secure, privacy-preserving AI with NVIDIA H100 GPUs

AI and large language models (LLMs) like ChatGPT are transforming how organizations operate, driving unprecedented levels of productivity and innovation. However, AI adoption can often be impeded by concerns surrounding data privacy and security. This is particularly true for highly regulated industries like financial services, healthcare, and the public sector.

Launching confidential LLM platform: Continuum AI

Today marks a significant milestone we unveil Continuum AI, the first confidential LLM platform, now publicly available at This platform features an intuitive chat interface, currently serving the open-source model Mistral 7B. In the upcoming weeks, the platform will expand to include additional state-of-the-art models such as Llama 3 70B, ensuring that users have access to the latest advancements in AI while maintaining full confidentiality.

Confidential computing: The future of trustworthy AI

Confidential computing is a groundbreaking paradigm where data remains encrypted even during processing, ensuring that sensitive information is never exposed. This technology enhances the capabilities of modern CPUs and cloud infrastructures. With the introduction of the NVIDIA Hopper architecture-based H100 Tensor Core GPU, NVIDIA extended confidentiality features to GPUs, creating the first AI accelerator designed for confidential computing.

Edgeless Systems: Pioneering software for Confidential AI

At Edgeless Systems, we develop cutting-edge infrastructure software that enables companies to harness the full potential of confidential computing. Our latest offering, Continuum, is a comprehensive framework that allows for the secure deployment of AI models. The software integrates confidential virtual machines, the confidentiality and integrity features of NVIDIA H100 GPUs, and advanced sandboxing technology, as well as popular AI inference services like NVIDIA Triton Inference Server.

A new era of Confidential AI

The launch of this platform underscores a new era in AI deployment, where the benefits of powerful LLMs can be realized without compromising data privacy and security. We are collaborating with NVIDIA to empower businesses across sectors to confidently integrate AI into their operations. The confidential LLM platform is not just a technological advancement; it is a pivotal step towards a future where organizations can securely utilize AI, even for the most sensitive data.

Visit to try out Continuum AI yourself, and join the waitlist to stay ahead on enterprise-grade confidential AI. Here you can find the technical documentation.

Related reading

View all