# LocalAI v2.27.0 — Release & Upgrade Intelligence
- **Product:** LocalAI (https://localai.io)
- **Version:** v2.27.0
- **Released:** Mar 31, 2025
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/localai/updates/v2.27.0/

## Executive Summary (TL;DR)
LocalAI v2.27.0. Source highlight: :rocket:  **LocalAI v2.27.0**

## New Features
- **VLLM Config Boost**: Added options to disable logging, set dtype, and enforce per-prompt media limits.
- feat(ui): detect model usage and display link
- feat(vllm): Additional vLLM config options (Disable logging, dtype, and Per-Prompt media limits)
- feat(ui): show only text models in the chat interface
- feat(ui): do also filter tts and image models
- feat(ui): paginate model gallery

## Improvements
- **Complete WebUI Redesign**: A fresh, modern interface with enhanced navigation and visuals.
- **Model Gallery Improvements**: Easier exploration with improved pagination and filtering.
- **Chat Interface Enhancements**: Cleaner layout, model-specific UI tweaks, and custom reply prefixes.
- **Performance Tweaks**: GGUF models now auto-detect context size, and Llama.cpp handles batch embeddings and SIGTERM gracefully.

## Bug Fixes
- **Stability Fixes**: Critical bug fixes in model initialization, embeddings handling, and GPU offloading.
- Resolved model icon display inconsistencies.
- Ensured proper handling of generated artifacts without API key restrictions.
- Optimized CLIP offloading and Llama.cpp process termination.
- fix: change initialization order of llama-cpp-avx512 to go before avx2 variant
- fix(coqui): pin transformers