# LocalAI v2.8.0 — Release & Upgrade Intelligence
- **Product:** LocalAI (https://localai.io)
- **Version:** v2.8.0
- **Released:** Feb 10, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/localai/updates/v2.8.0/

## Executive Summary (TL;DR)
LocalAI v2.8.0. Source highlight: This release adds support for Intel GPUs, and it deprecates old ggml-based backends which are by now superseded by llama.cpp (that now supports more architectures out-of-the-box). See also https://github.com/mudler/LocalAI/issues/1651.

## New Features
- feat(sycl): Add support for Intel GPUs with sycl (#1647)
- Drop old falcon backend (deprecated)
- :arrow_up: Update ggerganov/llama.cpp
- Drop ggml-based gpt2 and starcoder (supported by llama.cpp)
- feat: Use ubuntu as base for container images, drop deprecated ggml-transformers backends
- feat(mamba): Add bagel-dpo-2.8b

## Bug Fixes
- fix(Dockerfile): sycl dependencies
- fix (docs): fixed broken links `github/` -> `github.com/`
- Fix HTTP links in README.md
- Revert "fix(Dockerfile): sycl dependencies"