[Release Post] Self-Hosted Code Suggestions and Chat Now GA

Release Note

You can now host selected large language models (LLMs) in your own infrastructure and configure those models as the source for GitLab Duo Code Suggestions and Chat. This feature is now GA and available with an Ultimate and Duo Enterprise subscription on self-managed GitLab environments.

With GitLab Duo Self-Hosted, you can use models hosted either on-premise or in a private cloud as the source for GitLab Duo Chat or Code Suggestions. We currently support open-source Mistral models on vLLM or AWS Bedrock, Claude 3.5 Sonnet on AWS Bedrock, and OpenAI models on Azure OpenAI. By enabling self-hosted models, you can leverage the power of generative AI while maintaining complete data sovereignty and privacy.

Please leave feedback in issue #512753

Documentation: https://docs.gitlab.com/ee/administration/self_hosted_models/