# LocalAI v2.26.0 — Release & Upgrade Intelligence
- **Product:** LocalAI (https://localai.io)
- **Version:** v2.26.0
- **Released:** Feb 15, 2025
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/localai/updates/v2.26.0/

## Executive Summary (TL;DR)
LocalAI v2.26.0. Source highlight: :llama:  LocalAI v2.26.0!

## Breaking Changes & Deprecations
- It contains several cleanups, performance improvements and few breaking changes: old backends that are now superseded have been removed (for example, `vall-e-x`), while new backends have been added to expand the range of model architectures that LocalAI can support. While most of the changes are tested, if you encounter issues with the new backends or migrated ones please file a new issue.
- :warning: Breaking Changes :warning: - Several backends have been dropped and replaced for improved performance and compatibility. - `Vall-e-x` and `Openvoice` were deprecated and dropped.
- Breaking Changes 🛠 * chore(vall-e-x): Drop backend by @mudler in https://github.com/mudler/LocalAI/pull/4619 * feat(transformers): merge musicgen functionalities to a single backend by @mudler in https://github.com/mudler/LocalAI/pull/4620

## New Features
- **Lazy grammars (llama.cpp):** Added grammar triggers for llama.cpp: this allow models trained with specific tokens to enable grammar generation when such tokens are seen: this allows precise JSON generation but also consistent output when the model does not need to answer with a tool. For example, in the config file of the model triggers can be specified as such:
- **Function Argument Parsing Using Named Regex:** A new feature that allows parsing function arguments with named regular expressions, simplifying function calls.
- **Support for New Backends:** Added Kokoro, OutelTTS, and Fast-Whisper backends.
- **Diffusers Update:** Added support for Sana pipelines and image generation option overrides.
- **Machine Tag and Inference Timing:** Allows tracking machine performance during inference.
- **Tokenization:** Introduced tokenization support for llama.cpp to improve text processing.

## Improvements
- Several backends have been dropped and replaced for improved performance and compatibility.

## Bug Fixes
- Multiple fixes to improve stability, including enabling SYCL support for stablediffusion-ggml and consistent OpenAI stop reason returns.
- Improved context shift handling for llama.cpp and fixed gallery store overrides.
- fix(llama.cpp): disable mirostat as default
- fix(stablediffusion-ggml): correctly enable sycl
- fix(stablediffusion-ggml): enable oneapi before build
- fix(docs): add missing `-core` suffix to sycl images