Secure LLM inference: enforce access control on confidential data

What this post added

Details the architecture of the secure-inference project, which integrates with llm-d to provide adapter-based access control for LLM inference. It describes the two phases: training, where sensitive data is partitioned and LoRA adapters are created for each domain; and inference, where user requests are authenticated and authorized via JWT/SSO and Open Policy Agent, with appropriate adapters loaded based on semantic analysis of the query. Provides an example flow for a software engineer.