The Logos platform serves as a central gateway between users and AI models within a shared GPU infrastructure, hosting and serving models through vLLM. Currently, deploying new models requires manual intervention by the administrator, who must verify compatibility, resolve errors, and accept licensing agreements on behalf of all users. Users do not have visibility into the status of a model request, leaving them unable to make informed decisions about whether to wait, switch to an available model, or request an alternative.
This thesis addresses these challenges by extending the Logos platform with four components: automated compatibility pre-checks, structured error reporting, user licensing management, and a model request monitoring component.