v3.3.2

mudler/LocalAIv3.3.2Aug 4, 2025by mudler

AI Summary

Adds functionality to install backends from a local path and allows backends to exist without a metadata file. Includes documentation responsiveness fixes and a stable-diffusion bump.

Key Highlights

  • Backends can now be installed from a local path.
  • Backends no longer require a metadata file.
  • Improved table responsiveness in documentation.

New Features

  • Local path backend installation.
  • Metadata file flexibility for backends.

Full Release Notes

<!-- Release notes generated using configuration in .github/release.yml at master -->

## What's Changed
### Exciting New Features 🎉
* feat(backends): install from local path by @mudler in https://github.com/mudler/LocalAI/pull/5962
* feat(backends): allow backends to not have a metadata file by @mudler in https://github.com/mudler/LocalAI/pull/5963
### 📖 Documentation and examples
* fix(docs): Improve responsiveness of tables by @dedyf5 in https://github.com/mudler/LocalAI/pull/5954
### 👒 Dependencies
* chore(stable-diffusion): bump, set GGML_MAX_NAME by @mudler in https://github.com/mudler/LocalAI/pull/5961
* chore(build): Rename sycl to intel by @richiejp in https://github.com/mudler/LocalAI/pull/5964
### Other Changes
* docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/5956
* chore: :arrow_up: Update ggml-org/whisper.cpp to `0becabc8d68d9ffa6ddfba5240e38cd7a2642046` by @localai-bot in https://github.com/mudler/LocalAI/pull/5958
* chore: :arrow_up: Update ggml-org/llama.cpp to `5c0eb5ef544aeefd81c303e03208f768e158d93c` by @localai-bot in https://github.com/mudler/LocalAI/pull/5959
* chore: :arrow_up: Update ggml-org/llama.cpp to `d31192b4ee1441bbbecd3cbf9e02633368bdc4f5` by @localai-bot in https://github.com/mudler/LocalAI/pull/5965


**Full Changelog**: https://github.com/mudler/LocalAI/compare/v3.3.1...v3.3.2