Starstruk Logo MarkStarstruk

v3.6.0

mudler/LocalAIv3.6.0Oct 3, 2025by mudler

AI Summary

This release focuses on bug fixes for reranking models, introduces Kokoro support for L4T devices, and adds multilingual capabilities to the Chatterbox backend. It also expands the model gallery with Whisper Turbo, Qwen image edit, and IBM Granite series models.

Key Highlights

  • Fixed reranking models limited to 512 tokens in llama.cpp backend.
  • Added Kokoro backend support for L4T devices.
  • Chatterbox backend now supports multilingual text.
  • Added Whisper Turbo model via whisper.cpp.
  • Added multiple IBM Granite models to the gallery.

New Features

  • L4T device support for Kokoro backend.
  • Multilingual support in Chatterbox backend.
  • Whisper Turbo model integration.
  • IBM Granite model gallery additions (Granite 4.0 h-small, h-tiny, h-micro, micro).

Full Release Notes

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

## What's Changed
### Bug fixes :bug:
* fix: reranking models limited to 512 tokens in llama.cpp backend by @jongames in https://github.com/mudler/LocalAI/pull/6344
### Exciting New Features 🎉
* feat(kokoro): add support for l4t devices by @mudler in https://github.com/mudler/LocalAI/pull/6322
* feat(chatterbox): support multilingual by @mudler in https://github.com/mudler/LocalAI/pull/6240
### 🧠 Models
* chore(model gallery): add qwen-image-edit-2509 by @mudler in https://github.com/mudler/LocalAI/pull/6336
* chore(models): add whisper-turbo via whisper.cpp by @mudler in https://github.com/mudler/LocalAI/pull/6340
* chore(model gallery): add ibm-granite_granite-4.0-h-small by @mudler in https://github.com/mudler/LocalAI/pull/6373
* chore(model gallery): add ibm-granite_granite-4.0-h-tiny by @mudler in https://github.com/mudler/LocalAI/pull/6374
* chore(model gallery): add ibm-granite_granite-4.0-h-micro by @mudler in https://github.com/mudler/LocalAI/pull/6375
* chore(model gallery): add ibm-granite_granite-4.0-micro by @mudler in https://github.com/mudler/LocalAI/pull/6376
### 👒 Dependencies
* chore(deps): bump grpcio from 1.74.0 to 1.75.0 in /backend/python/transformers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6332
* chore(deps): bump securego/gosec from 2.22.8 to 2.22.9 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6324
* chore(deps): bump llama.cpp to '72b24d96c6888c609d562779a23787304ae4609c' by @mudler in https://github.com/mudler/LocalAI/pull/6349
* chore(deps): bump grpcio from 1.74.0 to 1.75.1 in /backend/python/coqui by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6353
* chore(deps): bump transformers from 4.48.3 to 4.56.2 in /backend/python/coqui by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6330
* chore(deps): bump grpcio from 1.74.0 to 1.75.1 in /backend/python/diffusers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6361
* chore(deps): bump grpcio from 1.74.0 to 1.75.1 in /backend/python/rerankers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6360
* chore(deps): bump grpcio from 1.74.0 to 1.75.1 in /backend/python/common/template by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6358
* chore(deps): bump grpcio from 1.74.0 to 1.75.1 in /backend/python/vllm by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6357
* chore(deps): bump grpcio from 1.74.0 to 1.75.1 in /backend/python/bark by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6359
* chore(deps): bump grpcio from 1.75.0 to 1.75.1 in /backend/python/transformers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6362
* chore(deps): bump grpcio from 1.74.0 to 1.75.1 in /backend/python/exllama2 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6356
### Other Changes
* chore: :arrow_up: Update ggml-org/llama.cpp to `7f766929ca8e8e01dcceb1c526ee584f7e5e1408` by @localai-bot in https://github.com/mudler/LocalAI/pull/6319
* docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/6318
* chore: :arrow_up: Update ggml-org/llama.cpp to `da30ab5f8696cabb2d4620cdc0aa41a298c54fd6` by @localai-bot in https://github.com/mudler/LocalAI/pull/6321
* chore: :arrow_up: Update ggml-org/llama.cpp to `1d0125bcf1cbd7195ad0faf826a20bc7cec7d3f4` by @localai-bot in https://github.com/mudler/LocalAI/pull/6335
* chore(cudss): add cudds to l4t images by @mudler in https://github.com/mudler/LocalAI/pull/6338
* chore: :arrow_up: Update ggml-org/llama.cpp to `4ae88d07d026e66b41e85afece74e88af54f4e66` by @localai-bot in https://github.com/mudler/LocalAI/pull/6339
* CI: disable build-testing on PRs against arm64 by @mudler in https://github.com/mudler/LocalAI/pull/6341
* chore(deps): bump llama.cpp to '835b2b915c52bcabcd688d025eacff9a07b65f52' by @mudler in https://github.com/mudler/LocalAI/pull/6347
* chore: :arrow_up: Update ggml-org/llama.cpp to `4807e8f96a61b2adccebd5e57444c94d18de7264` by @localai-bot in https://github.com/mudler/LocalAI/pull/6350
* chore: :arrow_up: Update ggml-org/llama.cpp to `bd0af02fc96c2057726f33c0f0daf7bb8f3e462a` by @localai-bot in https://github.com/mudler/LocalAI/pull/6352
* Revert "chore(deps): bump transformers from 4.48.3 to 4.56.2 in /backend/python/coqui" by @mudler in https://github.com/mudler/LocalAI/pull/6363
* chore: :arrow_up: Update ggml-org/whisper.cpp to `32be14f8ebfc0498c2c619182f0d7f4c822d52c4` by @localai-bot in https://github.com/mudler/LocalAI/pull/6354
* chore: :arrow_up: Update ggml-org/llama.cpp to `5f7e166cbf7b9ca928c7fad990098ef32358ac75` by @localai-bot in https://github.com/mudler/LocalAI/pull/6355
* chore: :arrow_up: Update ggml-org/llama.cpp to `b2ba81dbe07b6dbea9c96b13346c66973dede32c` by @localai-bot in https://github.com/mudler/LocalAI/pull/6366
* chore: :arrow_up: Update ggml-org/whisper.cpp to `8c0855fd6bb115e113c0dca6255ea05f774d35f7` by @localai-bot in https://github.com/mudler/LocalAI/pull/6365
* chore: :arrow_up: Update ggml-org/whisper.cpp to `7849aff7a2e1f4234aa31b01a1870906d5431959` by @localai-bot in https://github.com/mudler/LocalAI/pull/6367
* chore: :arrow_up: Update ggml-org/llama.cpp to `1fe4e38cc20af058ed320bd46cac934991190056` by @localai-bot in https://github.com/mudler/LocalAI/pull/6368
* chore: :arrow_up: Update ggml-org/llama.cpp to `d64c8104f090b27b1f99e8da5995ffcfa6b726e2` by @localai-bot in https://github.com/mudler/LocalAI/pull/6371

## New Contributors
* @jongames made their first contribution in https://github.com/mudler/LocalAI/pull/6344

**Full Changelog**: https://github.com/mudler/LocalAI/compare/v3.5.4...v3.6.0