v2.27.0

mudler/LocalAIv2.27.0Mar 31, 2025by mudler
AI Summary

Complete WebUI overhaul, AIO image updates, and support for new model architectures like Gemma 3 and Mistral.
Key Highlights

Complete WebUI redesign
AIO image updates with new default models
New model architectures (Gemma 3, Mistral, Deepseek)
GGUF context size auto-detection
VLLM configuration boost
New Features

VLLM config options (disable logging, dtype, media limits)
GGUF context size guessing
Full Release Notes

<!-- Release notes generated using configuration in .github/release.yml at master -->
# :rocket:  **LocalAI v2.27.0** 

<h1 align="center">
  <br>
<img src="https://github.com/user-attachments/assets/b3137b56-5661-4aa4-939f-53bde60a5b27" style="display: block;margin-left: auto;margin-right: auto;width: 50%;">
</h1>

Welcome to another exciting release of LocalAI v2.27.0! We've been working hard to bring you a fresh WebUI experience and a host of improvements under the hood. Get ready to explore new updates!

## :fire: AIO Images Updates

Check out the updated models we're now shipping with our All-in-One images:

**CPU All-in-One**:
- **Text-to-Text**: `llama3.1`
- **Embeddings**: `granite-embeddings`
- **Vision**: `minicpm`

**GPU All-in-One**:
- **Text-to-Text**: `localai-functioncall-qwen2.5-7b-v0.5` (our tiniest flagship model!)
- **Embeddings**: `granite-embeddings`
- **Vision**: `minicpm`

## 💻 WebUI Overhaul!

We've given the WebUI a brand-new look and feel. Have a look at the stunning new interface:

| Talk Interface | Generate Audio |
| --- | --- |
| ![Screenshot 2025-03-31 at 12-01-36 LocalAI - Talk](https://github.com/user-attachments/assets/9841b1ee-88af-4b96-8ec0-41b17364efa7) | ![Screenshot 2025-03-31 at 12-01-29 LocalAI - Generate audio with voice-en-us-ryan-low](https://github.com/user-attachments/assets/d729f6f4-0621-4715-bda3-35fe6e159524) |

| Models Overview | Generate Images |
| --- | --- |
| ![Screenshot 2025-03-31 at 12-01-20 LocalAI - Models](https://github.com/user-attachments/assets/3cf0b918-ba8e-498a-a3cd-485db5984325) | ![Screenshot 2025-03-31 at 12-31-41 LocalAI - Generate images with flux 1-dev](https://github.com/user-attachments/assets/6753d23d-218b-4e07-94b8-9e6c5a4f2311) |

| Chat Interface | API Overview |
| --- | --- |
| ![Screenshot 2025-03-31 at 11-57-44 LocalAI - Chat with localai-functioncall-qwen2 5-7b-v0 5](https://github.com/user-attachments/assets/048eab31-0f0c-4d52-a920-3715233f9bf3) | ![Screenshot 2025-03-31 at 11-57-23 LocalAI API - c2a39e3 (c2a39e3639227cfd94ffffe9f5691239acc275a8)](https://github.com/user-attachments/assets/2540e8ce-1a2c-4c12-800c-763bd9be247f) |

| Login | Swarm |
| --- | --- |
|![Screenshot 2025-03-31 at 12-09-59 ](https://github.com/user-attachments/assets/5af681b0-dd8e-4fe8-a234-a22f8a040547) | ![Screenshot 2025-03-31 at 12-10-39 LocalAI - P2P dashboard](https://github.com/user-attachments/assets/b9527176-63d6-4d2e-8ed1-7fde13a9b0ad) |

## How to Use

To get started with LocalAI, you can use our container images. Here’s how to run them with Docker:

```sh
# CPU only image:
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-cpu

# Nvidia GPU:
docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-gpu-nvidia-cuda-12

# CPU and GPU image (bigger size):
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest

# AIO images (pre-downloads a set of models ready for use, see https://localai.io/basics/container/)
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-cpu
```

Check out our [Documentation](https://localai.io/basics/container/) for more information.

## **Key Highlights:** 
- **Complete WebUI Redesign**: A fresh, modern interface with enhanced navigation and visuals.
- **Model Gallery Improvements**: Easier exploration with improved pagination and filtering.
- **AIO Image Updates**: Smoother deployments with updated models.
- **Stability Fixes**: Critical bug fixes in model initialization, embeddings handling, and GPU offloading.

## **What’s New :tada:** 
- **Chat Interface Enhancements**: Cleaner layout, model-specific UI tweaks, and custom reply prefixes.
- **Smart Model Detection**: Automatically links to relevant model documentation based on use.
- **Performance Tweaks**: GGUF models now auto-detect context size, and Llama.cpp handles batch embeddings and SIGTERM gracefully.
- **VLLM Config Boost**: Added options to disable logging, set dtype, and enforce per-prompt media limits.
- **New model architecture supported**: Gemma 3, Mistral, Deepseek

## **Bug Fixes :bug:** 
- Resolved model icon display inconsistencies.
- Ensured proper handling of generated artifacts without API key restrictions.
- Optimized CLIP offloading and Llama.cpp process termination.

## **Stay Tuned!**

We have some incredibly exciting features and updates lined up for you. While we can't reveal everything just yet. Keep an eye out for our upcoming announcements – you won't want to miss them!

<h1 align="center">
  <br>
<img src="https://github.com/user-attachments/assets/4498ed5f-9c49-4bdc-a258-a6dd3cf3faa3" style="display: block;margin-left: auto;margin-right: auto;width: 20%;" width=200>
</h1>

Do you like the new webui? let us know in the Github discussions!

Enjoy 🚀

## Full changelog :point_down: 

<details>

<summary>
:point_right: Click to expand :point_left: 
</summary>

## What's Changed
### Bug fixes :bug:
* fix: change initialization order of llama-cpp-avx512 to go before avx2 variant by @bhulsken in https://github.com/mudler/LocalAI/pull/4837
* fix(coqui): pin transformers by @mudler in https://github.com/mudler/LocalAI/pull/4875
* fix(ui): not all models have an Icon by @mudler in https://github.com/mudler/LocalAI/pull/4913
* fix(models): unify usecases identifications by @mudler in https://github.com/mudler/LocalAI/pull/4914
* fix(llama.cpp): correctly handle embeddings in batches by @mudler in https://github.com/mudler/LocalAI/pull/4957
* fix(routes): do not gate generated artifacts via key by @mudler in https://github.com/mudler/LocalAI/pull/4971
* fix(clip): do not imply GPU offload by default by @mudler in https://github.com/mudler/LocalAI/pull/5010
* fix(llama.cpp): properly handle sigterm by @mudler in https://github.com/mudler/LocalAI/pull/5099
### Exciting New Features 🎉
* feat(ui): detect model usage and display link by @mudler in https://github.com/mudler/LocalAI/pull/4864
* feat(vllm): Additional vLLM config options (Disable logging, dtype, and Per-Prompt media limits) by @TheDropZone in https://github.com/mudler/LocalAI/pull/4855
* feat(ui): show only text models in the chat interface by @mudler in https://github.com/mudler/LocalAI/pull/4869
* feat(ui): do also filter tts and image models by @mudler in https://github.com/mudler/LocalAI/pull/4871
* feat(ui): paginate model gallery by @mudler in https://github.com/mudler/LocalAI/pull/4886
* feat(ui): small improvements to chat interface by @mudler in https://github.com/mudler/LocalAI/pull/4907
* feat(ui): improve chat interface by @mudler in https://github.com/mudler/LocalAI/pull/4910
* feat(ui): improvements to index and models page by @mudler in https://github.com/mudler/LocalAI/pull/4918
* feat: allow to specify a reply prefix by @mudler in https://github.com/mudler/LocalAI/pull/4931
* feat(ui): complete design overhaul by @mudler in https://github.com/mudler/LocalAI/pull/4942
* feat(ui): remove api key handling and small ui adjustments by @mudler in https://github.com/mudler/LocalAI/pull/4948
* feat(aio): update AIO image defaults by @mudler in https://github.com/mudler/LocalAI/pull/5002
* feat(gguf): guess default context size from file by @mudler in https://github.com/mudler/LocalAI/pull/5089
### 🧠 Models
* chore(model gallery): add ozone-ai_0x-lite by @mudler in https://github.com/mudler/LocalAI/pull/4835
* chore: update Image generation docs and examples by @mudler in https://github.com/mudler/LocalAI/pull/4841
* chore(model gallery): add kubeguru-llama3.2-3b-v0.1 by @mudler in https://github.com/mudler/LocalAI/pull/4858
* chore(model gallery): add allenai_llama-3.1-tulu-3.1-8b by @mudler in https://github.com/mudler/LocalAI/pull/4859
* chore(model gallery): add nbeerbower_dumpling-qwen2.5-14b by @mudler in https://github.com/mudler/LocalAI/pull/4860
* chore(model gallery): add nbeerbower_dumpling-qwen2.5-32b-v2 by @mudler in https://github.com/mudler/LocalAI/pull/4861
* chore(model gallery): add nbeerbower_dumpling-qwen2.5-72b by @mudler in https://github.com/mudler/LocalAI/pull/4862
* chore(model gallery): add pygmalionai_pygmalion-3-12b by @mudler in https://github.com/mudler/LocalAI/pull/4866
* chore(model gallery): add open-r1_openr1-qwen-7b by @mudler in https://github.com/mudler/LocalAI/pull/4867
* chore(model gallery): add sentientagi_dobby-unhinged-llama-3.3-70b by @mudler in https://github.com/mudler/LocalAI/pull/4868
* chore(model gallery): add internlm_oreal-32b by @mudler in https://github.com/mudler/LocalAI/pull/4872
* chore(model gallery): add internlm_oreal-deepseek-r1-distill-qwen-7b by @mudler in https://github.com/mudler/LocalAI/pull/4873
* chore(model gallery): add internlm_oreal-7b by @mudler in https://github.com/mudler/LocalAI/pull/4874
* chore(model gallery): add smirki_uigen-t1.1-qwen-14b by @mudler in https://github.com/mudler/LocalAI/pull/4877
* chore(model gallery): add smirki_uigen-t1.1-qwen-7b by @mudler in https://github.com/mudler/LocalAI/pull/4878
* chore(model gallery): add l3.1-8b-rp-ink by @mudler in https://github.com/mudler/LocalAI/pull/4879
* chore(model gallery): add pocketdoc_dans-personalityengine-v1.2.0-24b by @mudler in https://github.com/mudler/LocalAI/pull/4880
* chore(model gallery): add rombo-org_rombo-llm-v3.0-qwen-72b by @mudler in https://github.com/mudler/LocalAI/pull/4882
* chore(model gallery): add ozone-ai_reverb-7b by @mudler in https://github.com/mudler/LocalAI/pull/4883
* chore(model gallery): add arcee-ai_arcee-maestro-7b-preview by @mudler in https://github.com/mudler/LocalAI/pull/4884
* chore(model gallery): add steelskull_l3.3-mokume-gane-r1-70b by @mudler in https://github.com/mudler/LocalAI/pull/4885
* chore(model gallery): add steelskull_l3.3-cu-mai-r1-70b by @mudler in https://github.com/mudler/LocalAI/pull/4892
* chore(model gallery): add steelskull_l3.3-san-mai-r1-70b by @mudler in https://github.com/mudler/LocalAI/pull/4893
* chore(model gallery): add nohobby_l3.3-prikol-70b-extra by @mudler in https://github.com/mudler/LocalAI/pull/4894
* chore(model gallery): add flux.1dev-abliteratedv2 by @mudler in https://github.com/mudler/LocalAI/pull/4895
* chore(model gallery): add sicariussicariistuff_phi-line_14b by @mudler in https://github.com/mudler/LocalAI/pull/4901
* chore(model gallery): add perplexity-ai_r1-1776-distill-llama-70b by @mudler in https://github.com/mudler/LocalAI/pull/4902
* chore(model gallery): add latitudegames_wayfarer-large-70b-llama-3.3 by @mudler in https://github.com/mudler/LocalAI/pull/4903
* chore(model gallery): add locutusque_thespis-llama-3.1-8b by @mudler in https://github.com/mudler/LocalAI/pull/4912
* chore(model gallery): add microsoft_phi-4-mini-instruct by @mudler in https://github.com/mudler/LocalAI/pull/4921
* chore(model gallery): add ozone-research_chirp-01 by @mudler in https://github.com/mudler/LocalAI/pull/4922
* chore(model gallery): add ozone-research_0x-lite by @mudler in https://github.com/mudler/LocalAI/pull/4923
* chore(model gallery): add allenai_olmocr-7b-0225-preview by @mudler in https://github.com/mudler/LocalAI/pull/4924
* chore(model gallery): add ibm-granite_granite-3.2-8b-instruct by @mudler in https://github.com/mudler/LocalAI/pull/4927
* chore(model gallery): add ibm-granite_granite-3.2-2b-instruct by @mudler in https://github.com/mudler/LocalAI/pull/4928
* chore(model gallery): add qihoo360_tinyr1-32b-preview by @mudler in https://github.com/mudler/LocalAI/pull/4929
* chore(model gallery): add thedrummer_fallen-llama-3.3-r1-70b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/4930
* chore(model gallery): add steelskull_l3.3-mokume-gane-r1-70b-v1.1 by @mudler in https://github.com/mudler/LocalAI/pull/4933
* chore(model gallery): update qihoo360_tinyr1-32b-preview by @mudler in https://github.com/mudler/LocalAI/pull/4937
* chore(model gallery): add l3.3-geneticlemonade-unleashed-70b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/4938
* chore(model gallery): add boomer_qwen_72b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/4939
* chore(model gallery): add llama-3.3-magicalgirl-2 by @mudler in https://github.com/mudler/LocalAI/pull/4940
* chore(model gallery): add azura-qwen2.5-32b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/4941
* chore(model gallery): add llama-3.1-8b-instruct-uncensored-delmat-i1 by @mudler in https://github.com/mudler/LocalAI/pull/4944
* chore(model gallery): add lolzinventor_meta-llama-3.1-8b-survivev3 by @mudler in https://github.com/mudler/LocalAI/pull/4945
* chore(model gallery): add llama-3.3-magicalgirl-2.5-i1 by @mudler in https://github.com/mudler/LocalAI/pull/4946
* chore(model gallery): add qwen_qwq-32b by @mudler in https://github.com/mudler/LocalAI/pull/4952
* chore(model gallery): add rombo-org_rombo-llm-v3.1-qwq-32b by @mudler in https://github.com/mudler/LocalAI/pull/4953
* chore(model gallery): add nomic-embed-text-v1.5 by @mudler in https://github.com/mudler/LocalAI/pull/4955
* chore(model gallery): add granite embeddings models by @mudler in https://github.com/mudler/LocalAI/pull/4956
* chore(model gallery): add steelskull_l3.3-electra-r1-70b by @mudler in https://github.com/mudler/LocalAI/pull/4960
* chore(model gallery): add huihui-ai_qwq-32b-abliterated by @mudler in https://github.com/mudler/LocalAI/pull/4961
* chore(model gallery): add goppa-ai_goppa-logillama by @mudler in https://github.com/mudler/LocalAI/pull/4962
* chore(model gallery): add tower-babel_babel-9b-chat by @mudler in https://github.com/mudler/LocalAI/pull/4964
* chore(model gallery): add llmevollama-3.1-8b-v0.1-i1 by @mudler in https://github.com/mudler/LocalAI/pull/4968
* chore(model gallery): add opencrystal-l3-15b-v2.1-i1 by @mudler in https://github.com/mudler/LocalAI/pull/4969
* chore(model gallery): add hyperllama3.1-v2-i1 by @mudler in https://github.com/mudler/LocalAI/pull/4970
* chore(model gallery): add openpipe_deductive-reasoning-qwen-14b by @mudler in https://github.com/mudler/LocalAI/pull/4994
* chore(model gallery): add openpipe_deductive-reasoning-qwen-32b by @mudler in https://github.com/mudler/LocalAI/pull/4995
* chore(model gallery): add thedrummer_gemmasutra-small-4b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/4997
* chore(model gallery): add open-r1_olympiccoder-32b by @mudler in https://github.com/mudler/LocalAI/pull/4998
* chore(model gallery): add open-r1_olympiccoder-7b by @mudler in https://github.com/mudler/LocalAI/pull/4999
* chore(model gallery): add trashpanda-org_qwq-32b-snowdrop-v0 by @mudler in https://github.com/mudler/LocalAI/pull/5000
* chore(model gallery): add gemma-3-27b-it by @mudler in https://github.com/mudler/LocalAI/pull/5003
* chore(model gallery): add gemma-3-12b-it by @mudler in https://github.com/mudler/LocalAI/pull/5007
* chore(model gallery): add gemma-3-4b-it by @mudler in https://github.com/mudler/LocalAI/pull/5008
* chore(model gallery): add gemma-3-1b-it by @mudler in https://github.com/mudler/LocalAI/pull/5009
* chore(model gallery): add models/qgallouedec_gemma-3-27b-it-codeforces-sft by @mudler in https://github.com/mudler/LocalAI/pull/5013
* chore(model gallery): add nousresearch_deephermes-3-mistral-24b-preview by @mudler in https://github.com/mudler/LocalAI/pull/5014
* chore(model gallery): add nousresearch_deephermes-3-llama-3-3b-preview by @mudler in https://github.com/mudler/LocalAI/pull/5015
* chore(model gallery): add prithivmlmods_viper-coder-32b-elite13 by @mudler in https://github.com/mudler/LocalAI/pull/5016
* chore(model gallery): add eurollm-9b-instruct by @mudler in https://github.com/mudler/LocalAI/pull/5017
* chore(model gallery): add allura-org_bigger-body-70b by @mudler in https://github.com/mudler/LocalAI/pull/5021
* chore(model gallery): add pocketdoc_dans-sakurakaze-v1.0.0-12b by @mudler in https://github.com/mudler/LocalAI/pull/5023
* chore(model gallery): add beaverai_mn-2407-dsk-qwqify-v0.1-12b by @mudler in https://github.com/mudler/LocalAI/pull/5024
* chore(model gallery): add readyart_forgotten-safeword-70b-3.6 by @mudler in https://github.com/mudler/LocalAI/pull/5027
* chore(model gallery): add mproj files for gemma3 models by @mudler in https://github.com/mudler/LocalAI/pull/5028
* chore(model gallery): add mlabonne_gemma-3-27b-it-abliterated by @mudler in https://github.com/mudler/LocalAI/pull/5031
* chore(model gallery): add mlabonne_gemma-3-12b-it-abliterated by @mudler in https://github.com/mudler/LocalAI/pull/5032
* chore(model gallery): add mlabonne_gemma-3-4b-it-abliterated by @mudler in https://github.com/mudler/LocalAI/pull/5033
* chore(model gallery): add soob3123_amoral-gemma3-12b by @mudler in https://github.com/mudler/LocalAI/pull/5034
* chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/5036
* chore(model gallery): add mistralai_mistral-small-3.1-24b-instruct-2503 by @mudler in https://github.com/mudler/LocalAI/pull/5039
* chore(model gallery): add gryphe_pantheon-rp-1.8-24b-small-3.1 by @mudler in https://github.com/mudler/LocalAI/pull/5040
* chore(model gallery): add nvidia_llama-3_3-nemotron-super-49b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/5041
* chore(model gallery): add gemma-3-4b-it-uncensored-dbl-x-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5043
* chore(model gallery): add rootxhacker_apollo-v3-32b by @mudler in https://github.com/mudler/LocalAI/pull/5044
* chore(model gallery): add samsungsailmontreal_bytecraft by @mudler in https://github.com/mudler/LocalAI/pull/5045
* chore(model gallery): add soob3123_amoral-gemma3-4b by @mudler in https://github.com/mudler/LocalAI/pull/5046
* chore(model gallery): add qwen-writerdemo-7b-s500-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5049
* chore(model gallery): add sao10k_llama-3.3-70b-vulpecula-r1 by @mudler in https://github.com/mudler/LocalAI/pull/5050
* chore(model gallery): add luvgpt_phi3-uncensored-chat by @mudler in https://github.com/mudler/LocalAI/pull/5051
* chore(model gallery): add knoveleng_open-rs3 by @mudler in https://github.com/mudler/LocalAI/pull/5054
* chore(model gallery): add thedrummer_fallen-gemma3-4b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/5055
* chore(model gallery): add thedrummer_fallen-gemma3-12b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/5056
* chore(model gallery): add thedrummer_fallen-gemma3-27b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/5057
* chore(model gallery): add huihui-ai_gemma-3-1b-it-abliterated by @mudler in https://github.com/mudler/LocalAI/pull/5058
* chore(model gallery): add mawdistical_mawdistic-nightlife-24b by @mudler in https://github.com/mudler/LocalAI/pull/5059
* chore(model gallery): add sicariussicariistuff_x-ray_alpha by @mudler in https://github.com/mudler/LocalAI/pull/5060
* chore(model gallery): add fiendish_llama_3b by @mudler in https://github.com/mudler/LocalAI/pull/5061
* chore(model gallery): add impish_llama_3b by @mudler in https://github.com/mudler/LocalAI/pull/5064
* chore(model gallery): add eximius_persona_5b by @mudler in https://github.com/mudler/LocalAI/pull/5065
* chore(model gallery): add dusk_rainbow by @mudler in https://github.com/mudler/LocalAI/pull/5066
* chore(model gallery): add jdineen_llama-3.1-8b-think by @mudler in https://github.com/mudler/LocalAI/pull/5069
* chore(model gallery): add helpingai_helpingai3-raw by @mudler in https://github.com/mudler/LocalAI/pull/5070
* chore(model gallery): add alamios_mistral-small-3.1-draft-0.5b by @mudler in https://github.com/mudler/LocalAI/pull/5071
* chore(model gallery): add gemma-3-glitter-12b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5074
* chore(model gallery): add blacksheep-24b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5075
* chore(model gallery): add textsynth-8b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5076
* chore(model gallery): add soob3123_amoral-gemma3-12b-v2 by @mudler in https://github.com/mudler/LocalAI/pull/5080
* chore(model gallery): gemma-3-starshine-12b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5081
* chore(model gallery): qwen2.5-14b-instruct-1m-unalign-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5082
* chore(model gallery): thoughtless-fallen-abomination-70b-r1-v4.1-i1 by @mudler in https://github.com/mudler/LocalAI/pull/5083
* chore(model gallery): fallen-safeword-70b-r1-v4.1 by @mudler in https://github.com/mudler/LocalAI/pull/5084
* chore(model gallery): add tarek07_legion-v2.1-llama-70b by @mudler in https://github.com/mudler/LocalAI/pull/5087
* chore(model gallery): add tesslate_tessa-t1-32b by @mudler in https://github.com/mudler/LocalAI/pull/5088
* chore(model gallery): add tesslate_tessa-t1-14b by @mudler in https://github.com/mudler/LocalAI/pull/5090
* chore(model gallery): add tesslate_tessa-t1-7b by @mudler in https://github.com/mudler/LocalAI/pull/5091
* chore(model gallery): add tesslate_tessa-t1-3b by @mudler in https://github.com/mudler/LocalAI/pull/5092
* chore(model gallery): add chaoticneutrals_very_berry_qwen2_7b by @mudler in https://github.com/mudler/LocalAI/pull/5093
* chore(model gallery): add galactic-qwen-14b-exp1 by @mudler in https://github.com/mudler/LocalAI/pull/5096
* chore(model gallery): add forgotten-abomination-70b-v5.0 by @mudler in https://github.com/mudler/LocalAI/pull/5097
* chore(model gallery): add hammer2.0-7b by @mudler in https://github.com/mudler/LocalAI/pull/5098
### 👒 Dependencies
* chore: :arrow_up: Update ggml-org/llama.cpp to `2eea03d86a2d132c8245468c26290ce07a27a8e8` by @localai-bot in https://github.com/mudler/LocalAI/pull/4839
* chore(deps): Bump edgevpn to v0.30.1 by @mudler in https://github.com/mudler/LocalAI/pull/4840
* chore: :arrow_up: Update ggml-org/llama.cpp to `73e2ed3ce3492d3ed70193dd09ae8aa44779651d` by @localai-bot in https://github.com/mudler/LocalAI/pull/4854
* chore: :arrow_up: Update ggml-org/llama.cpp to `63e489c025d61c7ca5ec06c5d10f36e2b76aaa1d` by @localai-bot in https://github.com/mudler/LocalAI/pull/4865
* chore: :arrow_up: Update ggml-org/llama.cpp to `d04e7163c85a847bc61d58c22f2c503596db7aa8` by @localai-bot in https://github.com/mudler/LocalAI/pull/4870
* chore: :arrow_up: Update ggml-org/llama.cpp to `c392e5094deaf2d1a7c18683214f007fad3fe42b` by @localai-bot in https://github.com/mudler/LocalAI/pull/4876
* chore: :arrow_up: Update ggml-org/llama.cpp to `51f311e057723b7454d0ebe20f545a1a2c4db6b2` by @localai-bot in https://github.com/mudler/LocalAI/pull/4881
* chore: :arrow_up: Update ggml-org/llama.cpp to `a28e0d5eb18c18e6a4598286158f427269b1444e` by @localai-bot in https://github.com/mudler/LocalAI/pull/4887
* chore(stable-diffusion-ggml): update, adapt upstream changes by @mudler in https://github.com/mudler/LocalAI/pull/4889
* chore: :arrow_up: Update ggml-org/llama.cpp to `7ad0779f5de84a68143b2c00ab5dc94a948925d3` by @localai-bot in https://github.com/mudler/LocalAI/pull/4890
* chore(deps): Bump appleboy/ssh-action from 1.2.0 to 1.2.1 by @dependabot in https://github.com/mudler/LocalAI/pull/4896
* chore(deps): Bump docs/themes/hugo-theme-relearn from `66bc366` to `02bba0f` by @dependabot in https://github.com/mudler/LocalAI/pull/4898
* chore: :arrow_up: Update ggml-org/llama.cpp to `7a2c913e66353362d7f28d612fd3c9d51a831eda` by @localai-bot in https://github.com/mudler/LocalAI/pull/4899
* chore: :arrow_up: Update ggml-org/llama.cpp to `d7cfe1ffe0f435d0048a6058d529daf76e072d9c` by @localai-bot in https://github.com/mudler/LocalAI/pull/4908
* chore: :arrow_up: Update ggml-org/llama.cpp to `a800ae46da2ed7dac236aa6bf2b595da6b6294b5` by @localai-bot in https://github.com/mudler/LocalAI/pull/4911
* chore: :arrow_up: Update ggml-org/llama.cpp to `b95c8af37ccf169b0a3216b7ed691af0534e5091` by @localai-bot in https://github.com/mudler/LocalAI/pull/4916
* chore: :arrow_up: Update ggml-org/llama.cpp to `06c2b1561d8b882bc018554591f8c35eb04ad30e` by @localai-bot in https://github.com/mudler/LocalAI/pull/4920
* chore: :arrow_up: Update ggml-org/llama.cpp to `1782cdfed60952f9ff333fc2ab5245f2be702453` by @localai-bot in https://github.com/mudler/LocalAI/pull/4926
* chore: :arrow_up: Update ggml-org/llama.cpp to `14dec0c2f29ae56917907dbf2eed6b19438d0a0e` by @localai-bot in https://github.com/mudler/LocalAI/pull/4932
* chore(deps): Bump docs/themes/hugo-theme-relearn from `02bba0f` to `4a4b60e` by @dependabot in https://github.com/mudler/LocalAI/pull/4934
* chore: :arrow_up: Update ggml-org/llama.cpp to `dfd6b2c0be191b3abe2fd9c1b25deff01c6249d8` by @localai-bot in https://github.com/mudler/LocalAI/pull/4936
* chore: :arrow_up: Update ggml-org/llama.cpp to `5bbe6a9fe9a8796a9389c85accec89dbc4d91e39` by @localai-bot in https://github.com/mudler/LocalAI/pull/4943
* chore(deps): update llama.cpp and sync with upstream changes by @mudler in https://github.com/mudler/LocalAI/pull/4950
* chore: :arrow_up: Update ggml-org/llama.cpp to `3d652bfddfba09022525067e672c3c145c074649` by @localai-bot in https://github.com/mudler/LocalAI/pull/4954
* chore: :arrow_up: Update ggml-org/llama.cpp to `7ab364390f92b0b8d83f69821a536b424838f3f8` by @localai-bot in https://github.com/mudler/LocalAI/pull/4959
* chore: :arrow_up: Update ggml-org/llama.cpp to `0fd7ca7a210bd4abc995cd728491043491dbdef7` by @localai-bot in https://github.com/mudler/LocalAI/pull/4963
* chore: :arrow_up: Update ggml-org/llama.cpp to `1e2f78a00450593e2dfa458796fcdd9987300dfc` by @localai-bot in https://github.com/mudler/LocalAI/pull/4966
* chore(deps): Bump intel-extension-for-pytorch from 2.3.110+xpu to 2.6.10+xpu in /backend/python/diffusers by @dependabot in https://github.com/mudler/LocalAI/pull/4973
* chore(deps): Bump appleboy/ssh-action from 1.2.1 to 1.2.2 by @dependabot in https://github.com/mudler/LocalAI/pull/4978
* chore(deps): Bump docs/themes/hugo-theme-relearn from `4a4b60e` to `9a020e7` by @dependabot in https://github.com/mudler/LocalAI/pull/4988
* chore: :arrow_up: Update ggml-org/llama.cpp to `2c9f833d17bb5b8ea89dec663b072b5420fc5438` by @localai-bot in https://github.com/mudler/LocalAI/pull/4991
* chore: :arrow_up: Update ggml-org/llama.cpp to `10f2e81809bbb69ecfe64fc8b4686285f84b0c07` by @localai-bot in https://github.com/mudler/LocalAI/pull/4996
* chore: :arrow_up: Update ggml-org/llama.cpp to `80a02aa8588ef167d616f76f1781b104c245ace0` by @localai-bot in https://github.com/mudler/LocalAI/pull/5004
* chore: :arrow_up: Update ggml-org/llama.cpp to `f08f4b3187b691bb08a8884ed39ebaa94e956707` by @localai-bot in https://github.com/mudler/LocalAI/pull/5006
* chore: :arrow_up: Update ggml-org/llama.cpp to `84d547554123a62e9ac77107cb20e4f6cc503af4` by @localai-bot in https://github.com/mudler/LocalAI/pull/5011
* chore: :arrow_up: Update ggml-org/llama.cpp to `9f2250ba722738ec0e6ab684636268a79160c854` by @localai-bot in https://github.com/mudler/LocalAI/pull/5019
* chore: :arrow_up: Update ggml-org/llama.cpp to `f4c3dd5daa3a79f713813cf1aabdc5886071061d` by @localai-bot in https://github.com/mudler/LocalAI/pull/5022
* chore: :arrow_up: Update ggml-org/llama.cpp to `8ba95dca2065c0073698afdfcda4c8a8f08bf0d9` by @localai-bot in https://github.com/mudler/LocalAI/pull/5026
* chore: :arrow_up: Update ggml-org/llama.cpp to `b1b132efcba216c873715c483809730bb253f4a1` by @localai-bot in https://github.com/mudler/LocalAI/pull/5029
* chore: :arrow_up: Update ggml-org/llama.cpp to `d84635b1b085d54d6a21924e6171688d6e3dfb46` by @localai-bot in https://github.com/mudler/LocalAI/pull/5035
* chore: :arrow_up: Update ggml-org/llama.cpp to `568013d0cd3d5add37c376b3d5e959809b711fc7` by @localai-bot in https://github.com/mudler/LocalAI/pull/5042
* chore: :arrow_up: Update ggml-org/llama.cpp to `e04643063b3d240b8c0fdba98677dff6ba346784` by @localai-bot in https://github.com/mudler/LocalAI/pull/5047
* chore: :arrow_up: Update ggml-org/llama.cpp to `4375415b4abf94fb36a5fd15f233ac0ee23c0bd1` by @localai-bot in https://github.com/mudler/LocalAI/pull/5052
* chore: :arrow_up: Update ggml-org/llama.cpp to `ba932dfb50cc694645b1a148c72f8c06ee080b17` by @localai-bot in https://github.com/mudler/LocalAI/pull/5053
* chore: :arrow_up: Update ggml-org/llama.cpp to `77f9c6bbe55fccd9ea567794024cb80943947901` by @localai-bot in https://github.com/mudler/LocalAI/pull/5062
* chore: :arrow_up: Update ggml-org/llama.cpp to `c95fa362b3587d1822558f7e28414521075f254f` by @localai-bot in https://github.com/mudler/LocalAI/pull/5068
* chore: :arrow_up: Update ggml-org/llama.cpp to `ef19c71769681a0b3dde6bc90911728376e5d236` by @localai-bot in https://github.com/mudler/LocalAI/pull/5073
* chore: :arrow_up: Update ggml-org/llama.cpp to `b3298fa47a2d56ae892127ea038942ab1cada190` by @localai-bot in https://github.com/mudler/LocalAI/pull/5077
* chore: :arrow_up: Update ggml-org/llama.cpp to `5dec47dcd411fdf815a3708fd6194e2b13d19006` by @localai-bot in https://github.com/mudler/LocalAI/pull/5079
* chore: :arrow_up: Update ggml-org/llama.cpp to `b4ae50810e4304d052e630784c14bde7e79e4132` by @localai-bot in https://github.com/mudler/LocalAI/pull/5085
* chore: :arrow_up: Update ggml-org/llama.cpp to `0bb2919335d00ff0bc79d5015da95c422de51f03` by @localai-bot in https://github.com/mudler/LocalAI/pull/5095
* chore: :arrow_up: Update ggml-org/llama.cpp to `4663bd353c61c1136cd8a97b9908755e4ab30cec` by @localai-bot in https://github.com/mudler/LocalAI/pull/5100
### Other Changes
* docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/4834
* feat: improve ui models list in the index by @mudler in https://github.com/mudler/LocalAI/pull/4863
* fix(ui): not all models comes from gallery by @mudler in https://github.com/mudler/LocalAI/pull/4915
* Revert "chore(deps): Bump intel-extension-for-pytorch from 2.3.110+xpu to 2.6.10+xpu in /backend/python/diffusers" by @mudler in https://github.com/mudler/LocalAI/pull/4992
* chore(deps): Bump grpcio to 1.71.0 by @mudler in https://github.com/mudler/LocalAI/pull/4993
* fix: ensure git-lfs is present by @dave-gray101 in https://github.com/mudler/LocalAI/pull/5078

</details>

## New Contributors
* @bhulsken made their first contribution in https://github.com/mudler/LocalAI/pull/4837
* @TheDropZone made their first contribution in https://github.com/mudler/LocalAI/pull/4855

**Full Changelog**: https://github.com/mudler/LocalAI/compare/v2.26.0...v2.27.0