Understand this story
On October 22, Cohere announced that the confidential computing feature of Cohere Model Vault has entered public beta. The feature runs on NVIDIA H100 GPUs on Microsoft Azure and targets enterprises handling sensitive data such as clinical records, financial information, privileged documents, and proprietary source code. According to Unite.AI, the feature uses encrypted request paths, remote attestation, and client-side verification so that operators at Azure, NVIDIA, and Cohere itself cannot read the memory of protected workloads. Cohere also stated that physical and side-channel attacks, availability, application-layer risks such as prompt injection, and metadata such as message size and timing are outside the scope of protection, and it plans to open-source the confidential inference stack. The feature is currently in public beta.
AI-generated from public reports
Latest development · Report
Cohere launches confidential computing public beta on Model VaultDevelopments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 23
Unite.AI
Cohere launches confidential computing public beta on Model Vault
On October 22, Cohere announced that the confidential computing feature of Cohere Model Vault has entered public beta, running on NVIDIA H100 GPUs on Microsoft Azure, targeting enterprises that handle sensitive data such as clinical records, financial information, privileged documents, and proprietary source code. Through encrypted request paths, remote attestation, and client-side verification, the feature prevents operators at Azure, NVIDIA, and Cohere itself from reading the memory of protected workloads. Cohere also stated that physical and side-channel attacks, availability, prompt injection, and other application-layer risks, as well as metadata such as message size and timing, are outside the scope of protection, and it plans to open-source the confidential inference stack.