[PSP-449] Add on-prem support to model-engine

[TarunRavikumar]

Add On-Premise Deployment Support

This PR adds support for on-premise deployments using Redis, MinIO storage.

Key Changes

• New on-prem configuration: Added onprem.yaml config file with settings for MinIO, Redis, and private registries
• Redis-based infrastructure: Implemented Redis task queues and on-prem queue endpoint delegate
• S3-compatible storage: Added support for MinIO and custom S3 endpoints with configurable addressing styles
• Container registry flexibility: Support for private registries with OnPremDockerRepository
• Database configuration: Environment variable-based PostgreSQL connection for on-prem deployments
• Improved logging: Enhanced error handling and debug logs in S3 file storage gateway

Why?

• We have contractual requirements to move our stack on-prem.
• MCPx needs model engine running locally for on-prem and ci/cd testing.

Next Steps

• There's probably more work we need to do in llm-engine to fully bring it to on-prem support. I've only tested that model engine can create new launch endpoints (and healthy pods) from our input docker image. This was what was needed for mcpx-go.

Linear

https://linear.app/scale-epd/issue/PSP-449/llm-engine-on-prem-support

[socket-security]

Review the following changes in direct dependencies. Learn more about Socket for GitHub.

Diff	Package	Supply Chain Security	Vulnerability	Quality	Maintenance	License
	psycopg2-binary@​2.9.3 ⏵ 2.9.10	+1

View full report

[MicahFulton]

do we need this file?