v3.5.0

<h1 align="center">
  <br>
  <img height="300" src="https://raw.githubusercontent.com/mudler/LocalAI/refs/heads/master/core/http/static/logo.png"> <br>
<br>
🚀 LocalAI 3.5.0
</h1>

Welcome to LocalAI 3.5.0! This release focuses on expanding backend support, improving usability, refining the overall experience, and keeping reducing footprint of LocalAI, to make it a truly portable, privacy-focused AI stack. We’ve added several new backends, enhanced the WebUI with new features, made significant performance improvements under the hood, and simplified LocalAI management with a new Launcher app (Alpha) available for Linux and MacOS.

## TL;DR – What’s New in LocalAI 3.5.0 🎉

- 🖼️ **Expanded Backend Support:** Welcome to MLX!  **mlx**, **mlx-audio**, **mlx-vlm** are now all available in LocalAI. We also added support to WAN for video generation, and a CPU and MPS version of the diffusers backend! Now you can generate and edit images from MacOS or if you don't have any GPU (albeit slow).
- ✨ **WebUI Enhancements:** Download model configurations, a manual model refresh button, streamlined error streaming during SSE events, and a stop button for running backends. Models now can also be imported and edited via the WebUI.
- 🚀 **Performance & Architecture:** Whisper backend has been rewritten in Purego with integrated Voice Activity Detection (VAD) for improved efficiency and stability. Stablediffusion also benefits from the Purego conversion.
- 🛠️ **Simplified Management:** New LocalAI Launcher App (Alpha) for easy installation, startup, updates, and access to the WebUI.
- ✅ **Bug Fixes & Stability:** Resolutions to AMD RX 9060XT ROCm errors, libomp linking issues, model loading problems on macOS, CUDA device detection improvements, and more.
- **Enhanced support for MacOS**: whisper, diffusers, llama.cpp, MLX (VLM, Audio, LLM), stable-diffusion.cpp will now work on MacOS!


## What’s New in Detail

### 🚀 New Backends and Model Support

We've significantly expanded the range of models you can run with LocalAI!

*   **mlx-audio:** Bring text to life with Kokoro’s voice models on MacOS with the power of MLX!. Install with the `mlx-audio` backend. Example configuration:
    ```yaml
    backend: mlx-audio
    name: kokoro-mlx
    parameters:
      model: prince-canuma/Kokoro-82M
      voice: "af_heart"
      known_usecases:
        - tts
    ```
*   **mlx-vlm:** Experiment with the latest VLM models. While we don't have any models in the gallery, it's really easy to configure, see https://github.com/mudler/LocalAI/pull/6119 for more details.
    ```yaml
    name: mlx-gemma
    backend: mlx-vlm
    parameters:
      model: "mlx-community/gemma-3n-E2B-it-4bit"
    template:
      use_tokenizer_template: true
    known_usecases:
    - chat
    ```
*   **WAN:** Generate videos with Wan2.1 or Wan 2.2 models using the `diffusers` backend, supporting both I2V and T2V.  Example configuration:
    ```yaml
    name: wan21
    f16: true
    backend: diffusers
    known_usecases:
      - video
    parameters:
      model: Wan-AI/Wan2.1-T2V-1.3B-Diffusers
    diffusers:
      cuda: true
      pipeline_type: WanPipeline
      step: 40
    options:
        - guidance_scale:5.0
        - num_frames:81
        - torch_dtype:bf16
    ```
*   **Diffusers CPU and MacOS Support:** Run diffusers models directly on your CPU without a GPU or with a Mac! This opens up LocalAI to a wider range of hardware configurations.

### ✨ WebUI Improvements

We've added several new features to make using LocalAI even easier:

*   **Download Model Config:** A "Get Config" button in the model gallery lets you download a model’s configuration file without installing the full model. This is perfect for custom setups and easier integration.
*   **Manual Model Refresh:** A new button allows you to manually refresh the on-disk YAML configuration, ensuring the WebUI always has the latest model information.
*   **Streamlined Error Handling:** Errors during SSE streaming events are now displayed directly to the user, providing better visibility and debugging information.
*   **Backend Stop Button:** Quickly stop running backends directly from the WebUI.

<img width="1009" height="262" alt="Screenshot From 2025-08-15 22-25-52" src="https://github.com/user-attachments/assets/84a9c0bf-5fc0-4436-b830-2e8bf03c04ea" />

*   **Model import and edit:** Now models can be edited and imported directly from the WebUI.

<img width="1920" height="917" alt="Screenshot 2025-08-14 at 22-28-59 LocalAI - Import Model" src="https://github.com/user-attachments/assets/d7b1b499-c30b-448e-831a-a80589ba4a27" />
<img width="1920" height="917" alt="Screenshot 2025-08-14 at 22-28-47 LocalAI - Edit Model gpt-oss-20b" src="https://github.com/user-attachments/assets/49e2961f-7cec-4fcd-a09a-2239256099aa" />

*   **Installed Backend List:** Now displays installed backends in the WebUI for easier access and management.





### 🚀 Performance & Architecture Improvements

*   **Purego Whisper Backend:** The Whisper backend has been rewritten in Purego for increased performance and stability. This also includes integrated Voice Activity Detection (VAD) for detecting speech.
*   **Purego Stablediffusion:** Similar to Whisper, Stablediffusion has been converted to Purego, improving its overall architecture and enabling better compatibility.

### 🛠️ Simplified Management – Introducing the LocalAI Launcher (Alpha)

We're excited to introduce the first version of the LocalAI Launcher! This application simplifies:

*   Installation
*   Startup/Shutdown
*   Updates
*   Access to the WebUI and Application Folder

<img width="216" height="292" alt="Screenshot From 2025-08-26 11-46-35" src="https://github.com/user-attachments/assets/7a22e2c3-1b4a-4d98-8299-6857fe8ae12f" />
<img width="274" height="301" alt="Screenshot From 2025-08-26 11-46-50" src="https://github.com/user-attachments/assets/349bf687-df34-4feb-8ef8-8da1eb4a823c" />
<img width="248" height="124" alt="Screenshot From 2025-08-26 11-46-21" src="https://github.com/user-attachments/assets/a7c216f2-3595-4eb9-b2ad-858095d1e2c7" />


**Please note:** The launcher is in Alpha and may have bugs.  The macOS build requires workarounds to run due to binaries not yet signed, and specific steps for running it are needed: https://discussions.apple.com/thread/253714860?answerId=257037956022#257037956022.

### ✅ Bug Fixes & Stability Improvements

*   **AMD RX 9060XT ROCm Error:** Fixed an issue causing errors with AMD RX 9060XT GPUs when using ROCm. This error, "ROCm error: invalid device function", occurred because of device function incompatibility.  The fix involves updating the ROCm image and ensuring the correct GPU targets are specified during compilation.  Recommended kernel versions and verification steps for GPU detection are available [here](link to troubleshooting doc if created).
*   **libomp Linking:** Resolved a missing `libomp.so` issue on macOS Docker containers.
*   **macOS Model Loading:** Addressed a problem where models could not be loaded on macOS. This was resolved by bundling necessary `libutf8` libraries.
*   **CUDA Device Detection:** Improved detection of available GPU resources.
*   **Flash Attention:** Set auto for flash_attention in llama.cpp, allowing the system to optimize performance.

### Additional Improvements

*   **System Backend:** Added a new "system" backend path (`LOCALAI_BACKENDS_SYSTEM_PATH` or via command-line arguments) defaulting to `/usr/share/localai/backends`. This allows specifying a read-only directory for backends, useful for package management and system-wide installations.
*   **P2P Model Sync:** Implemented automatic synchronization of installed models between LocalAI instances within a federation. Currently limited to models installed through the gallery, and configuration changes are *not* synced. Future improvements will address these limitations.
*   **Diffusers Image Source Handling:** Enhanced image source selection in the diffusers backend, prioritizing `ref_images` over `src` for more robust loading behavior.
*   **Darwin CI Builds:** Added support for building some Go-based backends (Stablediffusion and Whisper) on Darwin (macOS) in the CI pipeline.

## 🚨 Important Notes

*   **Launcher (Alpha):** The LocalAI Launcher is in its early stages of development. Please report any issues you encounter.  The MacOS build requires additional steps due to code signing.
*   **Model Configuration Updates:** Changes to model configuration files are not currently synchronized when using P2P model sync.

## The Complete Local Stack for Privacy-First AI

<table>
  <tr>
    <td width="30%" valign="top" align="center">
      <a href="https://github.com/mudler/LocalAI">
        <img src="https://raw.githubusercontent.com/mudler/LocalAI/refs/heads/master/core/http/static/logo.png" width="200" alt="LocalAI Logo">
        <h3>LocalAI</h3>
      </a>
    </td>
    <td width="70%" valign="top">
      <p>The free, Open Source OpenAI alternative. Acts as a drop-in replacement REST API compatible with OpenAI specifications for local AI inferencing. No GPU required.</p>
      <p><em>Link:</em> <a href="https://github.com/mudler/LocalAI">https://github.com/mudler/LocalAI</a></p>
    </td>
  </tr>
  <tr>
    <td width="30%" valign="top" align="center">
      <a href="https://github.com/mudler/LocalAGI">
         <img src="https://raw.githubusercontent.com/mudler/LocalAGI/refs/heads/main/webui/react-ui/public/logo_2.png" width="200" alt="LocalAGI Logo">
         <h3>LocalAGI</h3>
      </a>
    </td>
    <td width="70%" valign="top">
      <p>A powerful Local AI agent management platform. Serves as a drop-in replacement for OpenAI's Responses API, supercharged with advanced agentic capabilities and a no-code UI.</p>
      <p><em>Link:</em> <a href="https://github.com/mudler/LocalAGI">https://github.com/mudler/LocalAGI</a></p>
    </td>
  </tr>
  <tr>
    <td width="30%" valign="top" align="center">
      <a href="https://github.com/mudler/LocalRecall">
         <img src="https://raw.githubusercontent.com/mudler/LocalRecall/refs/heads/main/static/localrecall_horizontal.png" width="200" alt="LocalRecall Logo">
         <h3>LocalRecall</h3>
      </a>
    </td>
    <td width="70%" valign="top">
      <p>A RESTful API and knowledge base management system providing persistent memory and storage capabilities for AI agents. Designed to work alongside LocalAI and LocalAGI.</p>
      <p><em>Link:</em> <a href="https://github.com/mudler/LocalRecall">https://github.com/mudler/LocalRecall</a></p>
    </td>
  </tr>
</table>

## Thank you! ❤️

A massive **THANK YOU** to our incredible community and our sponsors! LocalAI has over **35.000 stars**, and LocalAGI has already rocketed past **1100+ stars**!

As a reminder, LocalAI is real FOSS (Free and Open Source Software) and its sibling projects are community-driven and not backed by VCs or a company. We rely on contributors donating their spare time and our sponsors to provide us the hardware! If you love open-source, privacy-first AI, please consider starring the repository, contributing code, reporting bugs, or spreading the word!

## Full changelog :point_down: 

<details>

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


## What's Changed
### Bug fixes :bug:
* fix(llama.cpp): support gfx1200 by @mudler in https://github.com/mudler/LocalAI/pull/6045
* fix: chmod grpc processes only if needed by @mudler in https://github.com/mudler/LocalAI/pull/6051
* fix: do not show invalid backends by @mudler in https://github.com/mudler/LocalAI/pull/6058
* fix(hipblas-llama.cpp): create symlink to libomp by @mudler in https://github.com/mudler/LocalAI/pull/6140
* fix: select portable environment if detected by @mudler in https://github.com/mudler/LocalAI/pull/6158
* fix: register backends to model-loader during installation by @mudler in https://github.com/mudler/LocalAI/pull/6159
### Exciting New Features 🎉
* chore(build): Convert stablediffusion-ggml backend to Purego by @richiejp in https://github.com/mudler/LocalAI/pull/5989
* fix(backend-detection): default to CPU if there is less than 4GB of GPU available by @mudler in https://github.com/mudler/LocalAI/pull/6057
* fix(llama-cpp/darwin): make sure to bundle `libutf8` libs by @mudler in https://github.com/mudler/LocalAI/pull/6060
* feat(backends): add system backend, refactor by @mudler in https://github.com/mudler/LocalAI/pull/6059
* feat(webui): add import/edit model page by @mudler in https://github.com/mudler/LocalAI/pull/6050
* chore(rocm): bump rocm image, add gfx1200 support by @mudler in https://github.com/mudler/LocalAI/pull/6065
* feat(ui): General improvements by @mudler in https://github.com/mudler/LocalAI/pull/6072
* Tune the "dark gray" font color in the webui to make it more readable by @lxnay in https://github.com/mudler/LocalAI/pull/6078
* feat(diffusers): add torchvision to support qwen-image-edit by @mudler in https://github.com/mudler/LocalAI/pull/6103
* feat(p2p): automatically sync installed models between instances by @mudler in https://github.com/mudler/LocalAI/pull/6108
* feat(img2img): Add support to Qwen Image Edit by @mudler in https://github.com/mudler/LocalAI/pull/6113
* feat(diffusers): add MPS version by @mudler in https://github.com/mudler/LocalAI/pull/6121
* feat: bundle python inside backends by @mudler in https://github.com/mudler/LocalAI/pull/6123
* Add mlx-vlm by @mudler in https://github.com/mudler/LocalAI/pull/6119
* feat(llama.cpp): Add gfx1201 support by @mudler in https://github.com/mudler/LocalAI/pull/6125
* feat(backends): add CPU variant for diffusers backend by @mudler in https://github.com/mudler/LocalAI/pull/6128
* chore(diffusers): support both src and reference_images in diffusers by @mudler in https://github.com/mudler/LocalAI/pull/6135
* feat(launcher): add LocalAI launcher app by @mudler in https://github.com/mudler/LocalAI/pull/6127
* feat(mlx-audio): Add mlx-audio backend by @mudler in https://github.com/mudler/LocalAI/pull/6138
* feat: Add a model refresh button to manually refresh on-disk yaml by @mcowger in https://github.com/mudler/LocalAI/pull/6150
* feat(diffusers): add support for wan2.2 by @mudler in https://github.com/mudler/LocalAI/pull/6153
* feat(whisper-cpp): Convert to Purego and add VAD by @richiejp in https://github.com/mudler/LocalAI/pull/6087
* chore: stream errors while streaming SSE by @mudler in https://github.com/mudler/LocalAI/pull/6160
* feat(gallery): Add 'Get Config' button for models by @mcowger in https://github.com/mudler/LocalAI/pull/6154
* feat(flash_attention): set auto for flash_attention in llama.cpp by @mudler in https://github.com/mudler/LocalAI/pull/6168
* chore(ci): Build some Go based backends on Darwin by @richiejp in https://github.com/mudler/LocalAI/pull/6164
### 🧠 Models
* chore(model gallery): add baichuan-inc_baichuan-m2-32 by @mudler in https://github.com/mudler/LocalAI/pull/6042
* chore(model gallery): add gemma-3-270m-it-qat by @mudler in https://github.com/mudler/LocalAI/pull/6063
* chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/6071
* chore(model gallery): add thedrummer_gemma-3-r1-27b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/6074
* chore(model gallery): add thedrummer_gemma-3-r1-12b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/6075
* chore(model gallery): add thedrummer_gemma-3-r1-4b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/6076
* chore(model gallery): add wingless_imp_8b-i1 by @mudler in https://github.com/mudler/LocalAI/pull/6077
* chore(model gallery): add impish_longtail_12b by @mudler in https://github.com/mudler/LocalAI/pull/6082
* chore(model gallery): add lfm2-vl-450m by @mudler in https://github.com/mudler/LocalAI/pull/6090
* chore(model gallery): add lfm2-vl-1.6b by @mudler in https://github.com/mudler/LocalAI/pull/6091
* chore(model gallery): add lfm2-1.2b by @mudler in https://github.com/mudler/LocalAI/pull/6092
* chore(model gallery): add opengvlab_internvl3_5-30b-a3b by @mudler in https://github.com/mudler/LocalAI/pull/6143
* chore(model gallery): add opengvlab_internvl3_5-14b by @mudler in https://github.com/mudler/LocalAI/pull/6144
* chore(model gallery): add opengvlab_internvl3_5-8b by @mudler in https://github.com/mudler/LocalAI/pull/6145
* chore(model gallery): add opengvlab_internvl3_5-4b by @mudler in https://github.com/mudler/LocalAI/pull/6146
* chore(model gallery): add opengvlab_internvl3_5-2b by @mudler in https://github.com/mudler/LocalAI/pull/6147
### 📖 Documentation and examples
* chore(docs): update list of supported backends by @mudler in https://github.com/mudler/LocalAI/pull/6134
### 👒 Dependencies
* chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/vllm by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6036
* chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/diffusers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6037
* chore(deps): bump sentence-transformers from 5.0.0 to 5.1.0 in /backend/python/transformers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6028
* chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/common/template by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6035
* chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/bark by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6033
* chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/rerankers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6022
* chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/exllama2 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6019
* chore(deps): bump oneccl-bind-pt from 2.3.100+xpu to 2.8.0+xpu in /backend/python/rerankers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6021
* chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/bark by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6043
* chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/common/template by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6034
* chore(deps): bump actions/checkout from 4 to 5 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6014
* chore(deps): bump actions/download-artifact from 4 to 5 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6015
* chore(deps): bump torch from 2.3.1+cxx11.abi to 2.8.0 in /backend/python/common/template by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6025
* chore(deps): bump oneccl-bind-pt from 2.3.100+xpu to 2.8.0+xpu in /backend/python/common/template by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6016
* chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/transformers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6013
* Revert "chore(build): Convert stablediffusion-ggml backend to Purego (#5989)" by @mudler in https://github.com/mudler/LocalAI/pull/6064
* chore(build): Use Purego with stablediffusion backend by @richiejp in https://github.com/mudler/LocalAI/pull/6067
* chore(deps): bump protobuf from 6.31.0 to 6.32.0 in /backend/python/transformers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6100
* chore(deps): bump actions/checkout from 4 to 5 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6101
* chore(deps): bump securego/gosec from 2.22.7 to 2.22.8 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6098
* chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/coqui by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6097
* chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/coqui by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6095
* chore(deps): bump torch from 2.3.1+cxx11.abi to 2.8.0 in /backend/python/coqui by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6099
* chore(deps): bump transformers from 4.48.3 to 4.55.2 in /backend/python/coqui by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6096
* chore(deps): bump the go_modules group with 4 updates by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/6161
### Other Changes
* docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/6046
* chore: :arrow_up: Update ggml-org/whisper.cpp to `5527454cdb3e15d7e2b8a6e2afcb58cb61651fd2` by @localai-bot in https://github.com/mudler/LocalAI/pull/6047
* chore: :arrow_up: Update ggml-org/llama.cpp to `f4586ee5986d6f965becb37876d6f3666478a961` by @localai-bot in https://github.com/mudler/LocalAI/pull/6048
* chore: :arrow_up: Update ggml-org/whisper.cpp to `16c2924cb2c4b5c9f79220aa7708eb5b346b029b` by @localai-bot in https://github.com/mudler/LocalAI/pull/6055
* chore: :arrow_up: Update ggml-org/llama.cpp to `29c8fbe4e05fd23c44950d0958299e25fbeabc5c` by @localai-bot in https://github.com/mudler/LocalAI/pull/6054
* chore(deps): bump llama.cpp to 'df36bce667bf14f8e538645547754386f9516326 by @mudler in https://github.com/mudler/LocalAI/pull/6062
* chore: :arrow_up: Update ggml-org/whisper.cpp to `040510a132f0a9b51d4692b57a6abfd8c9660696` by @localai-bot in https://github.com/mudler/LocalAI/pull/6069
* chore: :arrow_up: Update ggml-org/llama.cpp to `5e6229a8409ac786e62cb133d09f1679a9aec13e` by @localai-bot in https://github.com/mudler/LocalAI/pull/6070
* chore: :arrow_up: Update ggml-org/llama.cpp to `1fe00296f587dfca0957e006d146f5875b61e43d` by @localai-bot in https://github.com/mudler/LocalAI/pull/6079
* chore: :arrow_up: Update ggml-org/llama.cpp to `21c17b5befc5f6be5992bc87fc1ba99d388561df` by @localai-bot in https://github.com/mudler/LocalAI/pull/6084
* chore(ci): Build modified backends on PR by @richiejp in https://github.com/mudler/LocalAI/pull/6086
* chore: :arrow_up: Update ggml-org/llama.cpp to `6d7f1117e3e3285d0c5c11b5ebb0439e27920082` by @localai-bot in https://github.com/mudler/LocalAI/pull/6088
* chore: :arrow_up: Update ggml-org/whisper.cpp to `fc45bb86251f774ef817e89878bb4c2636c8a58f` by @localai-bot in https://github.com/mudler/LocalAI/pull/6089
* Revert "chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/coqui" by @mudler in https://github.com/mudler/LocalAI/pull/6102
* Revert "chore(deps): bump torch from 2.3.1+cxx11.abi to 2.8.0 in /backend/python/coqui" by @mudler in https://github.com/mudler/LocalAI/pull/6104
* Revert "chore(deps): bump transformers from 4.48.3 to 4.55.2 in /backend/python/coqui" by @mudler in https://github.com/mudler/LocalAI/pull/6105
* feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/6111
* chore: :arrow_up: Update ggml-org/llama.cpp to `fb22dd07a639e81c7415e30b146f545f1a2f2caf` by @localai-bot in https://github.com/mudler/LocalAI/pull/6112
* chore: :arrow_up: Update ggml-org/llama.cpp to `7a6e91ad26160dd6dfb33d29ac441617422f28e7` by @localai-bot in https://github.com/mudler/LocalAI/pull/6116
* chore: :arrow_up: Update ggml-org/llama.cpp to `cd36b5e5c7fed2a3ac671dd542d579ca40b48b54` by @localai-bot in https://github.com/mudler/LocalAI/pull/6118
* feat(mlx): add mlx backend by @mudler in https://github.com/mudler/LocalAI/pull/6049
* chore(deps): bump llama.cpp to '45363632cbd593537d541e81b600242e0b3d47fc' by @mudler in https://github.com/mudler/LocalAI/pull/6122
* chore: :arrow_up: Update ggml-org/llama.cpp to `710dfc465a68f7443b87d9f792cffba00ed739fe` by @localai-bot in https://github.com/mudler/LocalAI/pull/6126
* fix(rfdetr): use cpu torch for cpu builds by @mudler in https://github.com/mudler/LocalAI/pull/6129
* chore(Dockerfile): drop python from images by @mudler in https://github.com/mudler/LocalAI/pull/6130
* Revert "fix(rfdetr): use cpu torch for cpu builds" by @mudler in https://github.com/mudler/LocalAI/pull/6131
* chore: :arrow_up: Update ggml-org/whisper.cpp to `7745fcf32846006128f16de429cfe1677c963b30` by @localai-bot in https://github.com/mudler/LocalAI/pull/6136
* chore: :arrow_up: Update ggml-org/llama.cpp to `043fb27d3808766d8ea8195bbd12359727264402` by @localai-bot in https://github.com/mudler/LocalAI/pull/6137
* chore: :arrow_up: Update ggml-org/llama.cpp to `c4e9239064a564de7b94ee2b401ae907235a8fca` by @localai-bot in https://github.com/mudler/LocalAI/pull/6139
* chore(refactor): cli -> cmd, update docs by @mudler in https://github.com/mudler/LocalAI/pull/6148
* chore: :arrow_up: Update ggml-org/llama.cpp to `8b696861364360770e9f61a3422d32941a477824` by @localai-bot in https://github.com/mudler/LocalAI/pull/6151
* chore: :arrow_up: Update ggml-org/llama.cpp to `fbef0fad7a7c765939f6c9e322fa05cd52cf0c15` by @localai-bot in https://github.com/mudler/LocalAI/pull/6155
* chore: :arrow_up: Update ggml-org/llama.cpp to `c97dc093912ad014f6d22743ede0d4d7fd82365a` by @localai-bot in https://github.com/mudler/LocalAI/pull/6163
* feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/6162
* chore: :arrow_up: Update ggml-org/llama.cpp to `3d16b29c3bb1ec816ac0e782f20d169097063919` by @localai-bot in https://github.com/mudler/LocalAI/pull/6165
* chore: :arrow_up: Update ggml-org/llama.cpp to `e92d53b29e393fc4c0f9f1f7c3fe651be8d36faa` by @localai-bot in https://github.com/mudler/LocalAI/pull/6169
* chore(backends): add stablediffusion-ggml and whisper for metal by @mudler in https://github.com/mudler/LocalAI/pull/6173
* chore: :arrow_up: Update leejet/stable-diffusion.cpp to `4c6475f9176bf99271ccf5a2817b30a490b83db0` by @localai-bot in https://github.com/mudler/LocalAI/pull/6171
* fix(ci): Set default Darwin backend lang to python by @richiejp in https://github.com/mudler/LocalAI/pull/6175
* chore: :arrow_up: Update ggml-org/llama.cpp to `d4d8dbe383e8b9600cbe8b42016e3a4529b51219` by @localai-bot in https://github.com/mudler/LocalAI/pull/6172

</details>

## New Contributors
* @lxnay made their first contribution in https://github.com/mudler/LocalAI/pull/6078
* @mcowger made their first contribution in https://github.com/mudler/LocalAI/pull/6150

**Full Changelog**: https://github.com/mudler/LocalAI/compare/v3.4.0...v3.5.0