●Change8

Migrating to LocalAI v3.1.0

Version v3.1.0 introduces 4 breaking changes. This guide details how to update your code.

Released: 6/26/2025

4
Breaking Changes
4
Migration Steps
0
Affected Symbols

Breaking Changes

●Issue #1

Container images no longer bundle sources, significantly reducing image sizes. If rebuilding locally, follow the documentation to build from scratch.

●Issue #2

Default model path in container images changed from /build/models to /models/.

●Issue #3

Default backend path in container images changed from /build/backends to /backends/.

●Issue #4

Container image tag naming for development builds has been standardized: \`gpu-nvidia-cuda11\` (was \`cublas-cuda11\`), \`gpu-nvidia-cuda12\` (was \`cublas-cuda12\`), \`gpu-intel-f16\` (was \`sycl-f16\`), and \`gpu-intel-f32\` (was \`sycl-f32\`).

Migration Steps

  1. 1
    If you rely on bundled sources in container images, you must now rebuild locally following the documentation.
  2. 2
    Update paths referencing model directories in container images from \`/build/models\` to \`/models/\`.
  3. 3
    Update paths referencing backend directories in container images from \`/build/backends\` to \`/backends/\`.
  4. 4
    Update any scripts or configurations referencing old development container image tags (e.g., \`cublas-cuda11\`) to the new standardized names (e.g., \`gpu-nvidia-cuda11\`).

Release Summary

LocalAI 3.1 introduces support for Gemma 3n models and streamlines the container image structure by removing bundled sources, significantly reducing image size. This release also features meta-packages for easier backend installation and highlights the integrated LocalAI ecosystem.

Need More Details?

View the full release notes and all changes for LocalAI v3.1.0.

View Full Changelog