# LocalAI v2.22.0 — Release & Upgrade Intelligence
- **Product:** LocalAI (https://localai.io)
- **Version:** v2.22.0
- **Released:** Oct 12, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/localai/updates/v2.22.0/

## Executive Summary (TL;DR)
LocalAI v2.22.0. Source highlight: LocalAI v2.22.0 is out :partying_face:

## New Features
- feat(api): list loaded models in `/system`
- feat: Add Get Token Metrics to GRPC server
- refactor: ListModels Filtering Upgrade
- feat: track internally started models by ID
- feat: tokenization endpoint
- feat(multimodal): allow to template placeholders

## Improvements
- **Enhanced Multimodal Support**: Template placeholders are now available, offering more flexibility in multimodal applications
- chore(tests): improve rwkv tests and consume TEST_FLAKES

## Bug Fixes
- **Various bugfixes and improvements**: Fixed issues with dangling processes to ensure proper resource management and resolved channel closure issues in the base GRPC server.
- chore: simplify model loading
- fix(initializer): correctly reap dangling processes
- fix(base-grpc): close channel in base grpc server
- fix(vllm): bump cmake - vllm requires it
- fix(llama-cpp): consistently select fallback