v3.0.0

<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 3.0 – A New Era Begins
</h1>

Say hello to LocalAI 3.0 — our most ambitious release yet!

We’ve taken huge strides toward making LocalAI not just local, but limitless. Whether you're building LLM-powered agents, experimenting with audio pipelines, or deploying multimodal backends at scale — this release is for you.

Let’s walk you through what’s new. (And yes, there’s a lot to love.)

## TL;DR – What’s New in LocalAI 3.0.0 🎉

- 🧩 Backend Gallery: Install/remove backends on the fly, powered by OCI images — fully customizable and API-driven.
- 🎙️ Audio Support: Upload audio, PDFs, or text in the UI — plus new audio understanding models like Qwen Omni.
- 🌐 Realtime API: WebSocket support compatible with OpenAI clients, great for chat apps and agents.
- 🧠 Reasoning UI Boosts: Thinking indicators now show in chat for smart models.
- 📊 Dynamic VRAM Handling: Smarter GPU usage with automatic offloading.
- 🦙 Llama.cpp Upgrades: Now with reranking + multimodal via libmtmd.
- 📦 50+ New Models: Huge model gallery update with fresh LLMs across categories.
- 🐞 Bug Fixes: Streamed runes, template stability, better backend gallery UX.
- ❌ Deprecated: Extras images — replaced by the new backend system.

👉 Dive into the full changelog and docs below to explore more!

## 🧩 Introducing the Backend Gallery — Plug, Play, Power Up

![Screenshot From 2025-06-19 16-48-58](https://github.com/user-attachments/assets/2166d107-b1cf-4cb3-ad39-e2edc80338a8)

No more hunting for dependencies or custom hacks.

With the new Backend Gallery, you can now:

-  Install & remove backends at runtime or startup via API or directly from the WebUI
- Use custom galleries, just like you do for models
- Enjoy zero-config access to the default LocalAI gallery

Backends are standard OCI images — portable, composable, and totally DIY-friendly. Goodbye to "extras images" — hello to full backend modularity, even with Python-based dependencies.

📖 [Explore the Backend Gallery Docs](https://localai.io/backends)

### ⚠️ Important: Breaking Changes

From this release we will stop pushing `-extra` images containing python backends. You can now use standard images, and you will have only to pick the ones that are suited for your GPU. Additional backends can be installed via the backend gallery.

Here below some examples, note that the CI is still publishing the images so won't be available until jobs are processed, and the installation scripts will be updated right after images are publicly available.

### CPU only image:

```bash
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest
```

### NVIDIA GPU Images:

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

# CUDA 11
docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-gpu-nvidia-cuda-11

# NVIDIA Jetson (L4T) ARM64
docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-nvidia-l4t-arm64
```

### AMD GPU Images (ROCm):

```bash
docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-gpu-hipblas
```

### Intel GPU Images (oneAPI):

```bash
# Intel GPU with FP16 support
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-gpu-intel-f16

# Intel GPU with FP32 support
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-gpu-intel-f32
```

### Vulkan GPU Images:

```bash
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-gpu-vulkan
```

### AIO Images (pre-downloaded models):

```bash
# CPU version
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-cpu

# NVIDIA CUDA 12 version
docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-aio-gpu-nvidia-cuda-12

# NVIDIA CUDA 11 version
docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-aio-gpu-nvidia-cuda-11

# Intel GPU version
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-gpu-intel-f16

# AMD GPU version
docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-aio-gpu-hipblas
```

For more information about the AIO images and pre-downloaded models, see [Container Documentation](https://localai.io/basics/container/).

## 🧠 Smarter Reasoning, Smoother Chat

![Screenshot From 2025-06-19 16-58-27](https://github.com/user-attachments/assets/86a76557-eab0-4323-b928-2579692ac276)

- Realtime WebSocket API: OpenAI-style streaming support via WebSocket is here. Ideal for agents and chat apps.
- "Thinking" Tags: Reasoning models now show a visual "thinking" box during inference in the UI. Intuitive and satisfying.

## 🧠 Model Power-Up: VRAM Savvy + Multimodal Brains

Dynamic VRAM Estimation: LocalAI now adapts and offloads layers depending on your GPU’s capabilities. Optimal performance, no guesswork.
Llama.cpp upgrades also includes:
 - reranking
 - Enhanced multimodal support via libmtmd

## 🧪 New Models!

More than 50 new models joined the gallery, including:

-  🧠 skywork-or1-32b, rivermind-lux-12b, qwen3-embedding-*, llama3-24b-mullein, ultravox-v0_5, and more
-  🧬 Multimodal, reasoning, and domain-specific LLMs for every need
- 📦 Browse the latest additions in the [Model Gallery](https://models.localai.io)

## 🐞 Bugfixes & Polish

- Rune streaming is now buttery smooth
- Countless fixes across templates, inputs, CI, and realtime session updates
- Backend gallery UI is more stable and informative

## The Complete Local Stack for Privacy-First AI

With LocalAGI rejoining LocalAI alongside LocalRecall, our ecosystem provides a complete, open-source stack for private, secure, and intelligent AI operations:

<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>

## Join the Movement! ❤️

A massive **THANK YOU** to our incredible community and our sponsors! LocalAI has over **33,300 stars**, and LocalAGI has already rocketed past **750+ 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 repos, contributing code, reporting bugs, or spreading the word!

👉 **Check out the reborn LocalAGI v2 today:** [https://github.com/mudler/LocalAGI](https://github.com/mudler/LocalAGI)

LocalAI 3.0.0 is here. What will you build next?

## Full changelog :point_down: 

<details>

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


<!-- Release notes generated using configuration in .github/release.yml at master -->

## What's Changed
### Breaking Changes 🛠
* feat: Add backend gallery by @mudler in https://github.com/mudler/LocalAI/pull/5607
* chore(backends): move `bark-cpp` to the backend gallery by @mudler in https://github.com/mudler/LocalAI/pull/5682
### Bug fixes :bug:
* fix(ci): tag latest against cpu-only image by @mudler in https://github.com/mudler/LocalAI/pull/5362
* fix(flux): Set CFG=1 so that prompts are followed by @richiejp in https://github.com/mudler/LocalAI/pull/5378
* fix(template): we do not always have .Name by @mudler in https://github.com/mudler/LocalAI/pull/5508
* fix(input): handle correctly case where we pass by string list as inputs by @mudler in https://github.com/mudler/LocalAI/pull/5521
* fix(streaming): stream complete runes by @mudler in https://github.com/mudler/LocalAI/pull/5539
* fix(install.sh): vulkan docker tag by @halkeye in https://github.com/mudler/LocalAI/pull/5589
* fix(realtime): Use updated model on session update by @richiejp in https://github.com/mudler/LocalAI/pull/5604
* fix(backends gallery): propagate p2p settings to correctly draw menu by @mudler in https://github.com/mudler/LocalAI/pull/5684
### Exciting New Features 🎉
* feat(llama.cpp): upgrade and use libmtmd by @mudler in https://github.com/mudler/LocalAI/pull/5379
* feat(ui): add error page to display errors by @mudler in https://github.com/mudler/LocalAI/pull/5418
* feat(llama.cpp): add reranking by @mudler in https://github.com/mudler/LocalAI/pull/5396
* feat: Realtime API support reboot by @richiejp in https://github.com/mudler/LocalAI/pull/5392
* feat(llama.cpp): add support for audio input by @mudler in https://github.com/mudler/LocalAI/pull/5466
* feat(ui): add audio upload button in chat view by @mudler in https://github.com/mudler/LocalAI/pull/5526
* feat(ui): allow to upload PDF and text files, also add support to multiple input files by @mudler in https://github.com/mudler/LocalAI/pull/5538
* feat(ui): display thinking tags appropriately by @mudler in https://github.com/mudler/LocalAI/pull/5540
* feat: improve RAM estimation by using values from summary by @mudler in https://github.com/mudler/LocalAI/pull/5525
* feat(backend gallery): display download progress by @mudler in https://github.com/mudler/LocalAI/pull/5687
### 🧠 Models
* chore(model gallery): add skywork_skywork-or1-32b by @mudler in https://github.com/mudler/LocalAI/pull/5369
* chore(model gallery): add skywork_skywork-or1-7b by @mudler in https://github.com/mudler/LocalAI/pull/5370
* chore(model gallery): add thedrummer_snowpiercer-15b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/5371
* chore(model gallery): add thedrummer_rivermind-lux-12b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/5372
* chore(model gallery): add primeintellect_intellect-2 by @mudler in https://github.com/mudler/LocalAI/pull/5373
* fix: typos by @omahs in https://github.com/mudler/LocalAI/pull/5376
* chore(model gallery): add soob3123_grayline-qwen3-14b by @mudler in https://github.com/mudler/LocalAI/pull/5393
* chore(model gallery): add soob3123_grayline-qwen3-8b by @mudler in https://github.com/mudler/LocalAI/pull/5394
* chore(model gallery): add a-m-team_am-thinking-v1 by @mudler in https://github.com/mudler/LocalAI/pull/5395
* chore(model gallery): add thedrummer_valkyrie-49b-v1 by @mudler in https://github.com/mudler/LocalAI/pull/5410
* chore(model gallery): add facebook_kernelllm by @mudler in https://github.com/mudler/LocalAI/pull/5411
* chore(model gallery): add smolvlm-256m-instruct by @mudler in https://github.com/mudler/LocalAI/pull/5412
* chore(model gallery): add smolvlm-500m-instruct by @mudler in https://github.com/mudler/LocalAI/pull/5413
* chore(model gallery): add smolvlm-instruct by @mudler in https://github.com/mudler/LocalAI/pull/5414
* chore(model gallery): add smolvlm2-2.2b-instruct by @mudler in https://github.com/mudler/LocalAI/pull/5415
* chore(model gallery): add smolvlm2-500m-video-instruct by @mudler in https://github.com/mudler/LocalAI/pull/5416
* chore(model gallery): add smolvlm2-256m-video-instruct by @mudler in https://github.com/mudler/LocalAI/pull/5417
* chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/5422
* chore(model gallery): add nvidia_llama-3.1-nemotron-nano-4b-v1.1 by @mudler in https://github.com/mudler/LocalAI/pull/5427
* chore(model gallery): add mistralai_devstral-small-2505 by @mudler in https://github.com/mudler/LocalAI/pull/5428
* chore(model gallery): add delta-vector_archaeo-12b-v2 by @mudler in https://github.com/mudler/LocalAI/pull/5429
* chore(model gallery): add arliai_qwq-32b-arliai-rpr-v4 by @mudler in https://github.com/mudler/LocalAI/pull/5443
* chore(model gallery): add whiterabbitneo_whiterabbitneo-v3-7b by @mudler in https://github.com/mudler/LocalAI/pull/5444
* chore(model gallery): add vulpecula-4b by @mudler in https://github.com/mudler/LocalAI/pull/5445
* chore(model gallery): add medgemma-4b-it by @mudler in https://github.com/mudler/LocalAI/pull/5460
* chore(model gallery): add medgemma-27b-text-it by @mudler in https://github.com/mudler/LocalAI/pull/5461
* chore(model gallery): add allura-org_q3-30b-a3b-pentiment by @mudler in https://github.com/mudler/LocalAI/pull/5462
* chore(model gallery): add allura-org_q3-30b-a3b-designant by @mudler in https://github.com/mudler/LocalAI/pull/5502
* chore(model gallery): add luckyrp-24b by @mudler in https://github.com/mudler/LocalAI/pull/5503
* chore(model gallery): add mrm8488_qwen3-14b-ft-limo by @mudler in https://github.com/mudler/LocalAI/pull/5504
* chore(model gallery): add llama3-24b-mullein-v1 by @mudler in https://github.com/mudler/LocalAI/pull/5505
* chore(model gallery): add ms-24b-mullein-v0 by @mudler in https://github.com/mudler/LocalAI/pull/5506
* chore(model gallery): add qwen2.5-omni-7b by @mudler in https://github.com/mudler/LocalAI/pull/5513
* chore(model gallery): add pku-ds-lab_fairyr1-14b-preview by @mudler in https://github.com/mudler/LocalAI/pull/5516
* chore(model gallery): add pku-ds-lab_fairyr1-32b by @mudler in https://github.com/mudler/LocalAI/pull/5517
* chore(model gallery): add moondream2-20250414 by @mudler in https://github.com/mudler/LocalAI/pull/5518
* chore(model gallery): add arcee-ai_homunculus by @mudler in https://github.com/mudler/LocalAI/pull/5577
* chore(model gallery): add nvidia_nemotron-research-reasoning-qwen-1.5b by @mudler in https://github.com/mudler/LocalAI/pull/5578
* chore(model gallery): add e-n-v-y_legion-v2.1-llama-70b-elarablated-v0.8-hf by @mudler in https://github.com/mudler/LocalAI/pull/5579
* chore(model gallery): add deepseek-ai_deepseek-r1-0528-qwen3-8b by @mudler in https://github.com/mudler/LocalAI/pull/5580
* chore(model gallery): add goekdeniz-guelmez_josiefied-qwen3-14b-abliterated-v3 by @mudler in https://github.com/mudler/LocalAI/pull/5590
* chore(model gallery): add ultravox-v0_5-llama-3_2-1b by @mudler in https://github.com/mudler/LocalAI/pull/5591
* chore(model gallery): add ultravox-v0_5-llama-3_1-8b by @mudler in https://github.com/mudler/LocalAI/pull/5592
* chore(model gallery): add open-thoughts_openthinker3-7b by @mudler in https://github.com/mudler/LocalAI/pull/5595
* chore(model gallery): add nbeerbower_qwen3-gutenberg-encore-14b by @mudler in https://github.com/mudler/LocalAI/pull/5596
* chore(model gallery): add akhil-theerthala_kuvera-8b-v0.1.0 by @mudler in https://github.com/mudler/LocalAI/pull/5600
* chore(model gallery): add qwen2.5-omni-3b by @mudler in https://github.com/mudler/LocalAI/pull/5606
* chore(model gallery): add kwaipilot_kwaicoder-autothink-preview by @mudler in https://github.com/mudler/LocalAI/pull/5627
* chore(model gallery): add sophosympatheia_strawberrylemonade-l3-70b-v1.0 by @mudler in https://github.com/mudler/LocalAI/pull/5628
* chore(model gallery): add mistralai_magistral-small-2506 by @mudler in https://github.com/mudler/LocalAI/pull/5629
* chore(model gallery): add baai_robobrain2.0-7b by @mudler in https://github.com/mudler/LocalAI/pull/5630
* chore(model gallery): add openbuddy_openbuddy-r1-0528-distill-qwen3-32b-preview0-qat by @mudler in https://github.com/mudler/LocalAI/pull/5631
* chore(model gallery): add qwen3-embedding-4b by @mudler in https://github.com/mudler/LocalAI/pull/5632
* chore(model gallery): add qwen3-embedding-8b by @mudler in https://github.com/mudler/LocalAI/pull/5633
* chore(model gallery): add qwen3-embedding-0.6b by @mudler in https://github.com/mudler/LocalAI/pull/5634
* chore(model gallery): add yanfei-v2-qwen3-32b by @mudler in https://github.com/mudler/LocalAI/pull/5639
### 📖 Documentation and examples
* chore(docs/install.sh): image changes by @mudler in https://github.com/mudler/LocalAI/pull/5354
* updating the documentation on fine tuning and advanced guide.  by @TheDarkTrumpet in https://github.com/mudler/LocalAI/pull/5420
### 👒 Dependencies
* chore: :arrow_up: Update ggml-org/whisper.cpp to `e41bc5c61ae66af6be2bd7011769bb821a83e8ae` by @localai-bot in https://github.com/mudler/LocalAI/pull/5357
* chore: :arrow_up: Update ggml-org/llama.cpp to `de4c07f93783a1a96456a44dc16b9db538ee1618` by @localai-bot in https://github.com/mudler/LocalAI/pull/5358
* chore: :arrow_up: Update ggml-org/whisper.cpp to `f89056057511a1657af90bb28ef3f21e5b1f33cd` by @localai-bot in https://github.com/mudler/LocalAI/pull/5364
* chore: :arrow_up: Update ggml-org/whisper.cpp to `f389d7e3e56bbbfec49fd333551927a0fcbb7213` by @localai-bot in https://github.com/mudler/LocalAI/pull/5367
* chore: :arrow_up: Update ggml-org/whisper.cpp to `20a20decd94badfd519a07ea91f0bba8b8fc4dea` by @localai-bot in https://github.com/mudler/LocalAI/pull/5374
* chore: :arrow_up: Update ggml-org/whisper.cpp to `d1f114da61b1ae1e70b03104fad42c9dd666feeb` by @localai-bot in https://github.com/mudler/LocalAI/pull/5381
* chore: :arrow_up: Update ggml-org/llama.cpp to `e3a7cf6c5bf6a0a24217f88607b06e4405a2b5d9` by @localai-bot in https://github.com/mudler/LocalAI/pull/5384
* chore: :arrow_up: Update ggml-org/llama.cpp to `6a2bc8bfb7cd502e5ebc72e36c97a6f848c21c2c` by @localai-bot in https://github.com/mudler/LocalAI/pull/5390
* chore: :arrow_up: Update ggml-org/whisper.cpp to `62dc8f7d7b72ca8e75c57cd6a100712c631fa5d5` by @localai-bot in https://github.com/mudler/LocalAI/pull/5398
* chore: :arrow_up: Update ggml-org/llama.cpp to `b7a17463ec190aeee7b9077c606c910fb4688b84` by @localai-bot in https://github.com/mudler/LocalAI/pull/5399
* chore: :arrow_up: Update ggml-org/llama.cpp to `8e186ef0e764c7a620e402d1f76ebad60bf31c49` by @localai-bot in https://github.com/mudler/LocalAI/pull/5423
* chore: :arrow_up: Update ggml-org/whisper.cpp to `bd1cb0c8e3a04baa411dc12c1325b6a9f12ee7f4` by @localai-bot in https://github.com/mudler/LocalAI/pull/5424
* chore: :arrow_up: Update ggml-org/whisper.cpp to `78b31ca7824500e429ba026c1a9b48e0b41c50cb` by @localai-bot in https://github.com/mudler/LocalAI/pull/5439
* chore: :arrow_up: Update ggml-org/llama.cpp to `8a1d206f1d2b4e45918b589f3165b4be232f7ba8` by @localai-bot in https://github.com/mudler/LocalAI/pull/5440
* chore: :arrow_up: Update ggml-org/whisper.cpp to `13d92d08ae26031545921243256aaaf0ee057943` by @localai-bot in https://github.com/mudler/LocalAI/pull/5449
* chore: :arrow_up: Update ggml-org/llama.cpp to `d13d0f6135803822ec1cd7e3efb49360b88a1bdf` by @localai-bot in https://github.com/mudler/LocalAI/pull/5448
* chore(deps): bump llama.cpp to 'fef693dc6b959a8e8ba11558fbeaad0b264dd457' by @mudler in https://github.com/mudler/LocalAI/pull/5467
* chore: :arrow_up: Update ggml-org/whisper.cpp to `ea9f206f18d86c4eb357db9fdc52e4d9dc24435e` by @localai-bot in https://github.com/mudler/LocalAI/pull/5464
* chore: :arrow_up: Update ggml-org/llama.cpp to `a26c4cc11ec7c6574e3691e90ecdbd67deeea35b` by @localai-bot in https://github.com/mudler/LocalAI/pull/5500
* chore: :arrow_up: Update ggml-org/llama.cpp to `a3c30846e410c91c11d7bf80978795a03bb03dee` by @localai-bot in https://github.com/mudler/LocalAI/pull/5509
* chore: :arrow_up: Update ggml-org/whisper.cpp to `0ed00d9d30e8c984936ff9ed9a4fcd475d6d82e5` by @localai-bot in https://github.com/mudler/LocalAI/pull/5510
* chore: :arrow_up: Update ggml-org/llama.cpp to `d98f2a35fcf4a8d3e660ad48cd19e2a1f3d5b2ef` by @localai-bot in https://github.com/mudler/LocalAI/pull/5514
* chore: :arrow_up: Update ggml-org/whisper.cpp to `1f5fdbecb411a61b8576242e5170c5ecef24b05a` by @localai-bot in https://github.com/mudler/LocalAI/pull/5515
* chore: :arrow_up: Update ggml-org/whisper.cpp to `e5e900dd00747f747143ad30a697c8f21ddcd59e` by @localai-bot in https://github.com/mudler/LocalAI/pull/5522
* chore(deps): bump llama.cpp to 'e83ba3e460651b20a594e9f2f0f0bffb998d3ce1 by @mudler in https://github.com/mudler/LocalAI/pull/5527
* chore: :arrow_up: Update ggml-org/whisper.cpp to `98dfe8dc264b7d0d1daccfff9a9c043bcc2ece4b` by @localai-bot in https://github.com/mudler/LocalAI/pull/5542
* chore(deps): bump llama.cpp to 'e562eece7cb476276bfc4cbb18deb7c0369b2233' by @mudler in https://github.com/mudler/LocalAI/pull/5552
* chore: :arrow_up: Update ggml-org/whisper.cpp to `7fd6fa809749078aa00edf945e959c898f2bd1af` by @localai-bot in https://github.com/mudler/LocalAI/pull/5556
* chore: :arrow_up: Update ggml-org/whisper.cpp to `e05af2457b7b4134ee626dc044294a19b096e62f` by @localai-bot in https://github.com/mudler/LocalAI/pull/5569
* chore(deps): bump llama.cpp to '363757628848a27a435bbf22ff9476e9aeda5f40' by @mudler in https://github.com/mudler/LocalAI/pull/5571
* chore: :arrow_up: Update ggml-org/llama.cpp to `7e00e60ef86645a01fda738fef85b74afa016a34` by @localai-bot in https://github.com/mudler/LocalAI/pull/5574
* chore: :arrow_up: Update ggml-org/whisper.cpp to `82f461eaa4e6a1ba29fc0dbdaa415a9934ee8a1d` by @localai-bot in https://github.com/mudler/LocalAI/pull/5575
* chore(deps): bump GrantBirki/git-diff-action from 2.8.0 to 2.8.1 by @dependabot in https://github.com/mudler/LocalAI/pull/5564
* chore: :arrow_up: Update ggml-org/llama.cpp to `0d3984424f2973c49c4bcabe4cc0153b4f90c601` by @localai-bot in https://github.com/mudler/LocalAI/pull/5585
* chore: :arrow_up: Update ggml-org/whisper.cpp to `799eacdde40b3c562cfce1508da1354b90567f8f` by @localai-bot in https://github.com/mudler/LocalAI/pull/5586
* chore: :arrow_up: Update ggml-org/llama.cpp to `1caae7fc6c77551cb1066515e0f414713eebb367` by @localai-bot in https://github.com/mudler/LocalAI/pull/5593
* chore: :arrow_up: Update ggml-org/whisper.cpp to `b175baa665bc35f97a2ca774174f07dfffb84e19` by @localai-bot in https://github.com/mudler/LocalAI/pull/5597
* chore: :arrow_up: Update ggml-org/llama.cpp to `745aa5319b9930068aff5e87cf5e9eef7227339b` by @localai-bot in https://github.com/mudler/LocalAI/pull/5598
* chore: :arrow_up: Update ggml-org/llama.cpp to `5787b5da57e54dba760c2deeac1edf892e8fc450` by @localai-bot in https://github.com/mudler/LocalAI/pull/5601
* chore: :arrow_up: Update ggml-org/llama.cpp to `247e5c6e447707bb4539bdf1913d206088a8fc69` by @localai-bot in https://github.com/mudler/LocalAI/pull/5605
* chore: :arrow_up: Update ggml-org/whisper.cpp to `d78f08142381c1460604713e2f2ddf3331c7d816` by @localai-bot in https://github.com/mudler/LocalAI/pull/5619
* chore: :arrow_up: Update ggml-org/llama.cpp to `3678b838bb71eaccbaeb479ff38c2e12bfd2f960` by @localai-bot in https://github.com/mudler/LocalAI/pull/5620
* chore: :arrow_up: Update ggml-org/whisper.cpp to `2679bec6e09231c6fd59715fcba3eebc9e2f6076` by @localai-bot in https://github.com/mudler/LocalAI/pull/5625
* chore: :arrow_up: Update ggml-org/whisper.cpp to `ebbc874e85b518f963a87612f6d79f5c71a55e84` by @localai-bot in https://github.com/mudler/LocalAI/pull/5635
* chore: :arrow_up: Update ggml-org/llama.cpp to `ed52f3668e633423054a4eab61bb7efee47025ab` by @localai-bot in https://github.com/mudler/LocalAI/pull/5636
* chore: :arrow_up: Update ggml-org/whisper.cpp to `705db0f728310c32bc96f4e355e2b18076932f75` by @localai-bot in https://github.com/mudler/LocalAI/pull/5643
* chore: :arrow_up: Update ggml-org/llama.cpp to `3cb203c89f60483e349f841684173446ed23c28f` by @localai-bot in https://github.com/mudler/LocalAI/pull/5644
* chore: :arrow_up: Update ggml-org/llama.cpp to `30e5b01de2a0bcddc7c063c8ef0802703a958417` by @localai-bot in https://github.com/mudler/LocalAI/pull/5659
* chore(deps): bump securego/gosec from 2.22.4 to 2.22.5 by @dependabot in https://github.com/mudler/LocalAI/pull/5663
* chore: :arrow_up: Update ggml-org/whisper.cpp to `2a4d6db7d90899aff3d58d70996916968e4e0d27` by @localai-bot in https://github.com/mudler/LocalAI/pull/5661
* chore(deps): bump llama.cpp to 'e434e69183fd9e1031f4445002083178c331a28b by @mudler in https://github.com/mudler/LocalAI/pull/5665
* chore: :arrow_up: Update ggml-org/whisper.cpp to `f3ff80ea8da044e5b8833e7ba54ee174504c518d` by @localai-bot in https://github.com/mudler/LocalAI/pull/5677
* chore: :arrow_up: Update ggml-org/llama.cpp to `860a9e4eeff3eb2e7bd1cc38f65787cc6c8177af` by @localai-bot in https://github.com/mudler/LocalAI/pull/5678
* chore: :arrow_up: Update ggml-org/llama.cpp to `8d947136546773f6410756f37fcc5d3e65b8135d` by @localai-bot in https://github.com/mudler/LocalAI/pull/5685
* chore: :arrow_up: Update ggml-org/whisper.cpp to `ecb8f3c2b4e282d5ef416516bcbfb92821f06bf6` by @localai-bot in https://github.com/mudler/LocalAI/pull/5686
### Other Changes
* docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/5363
* chore: memoize detected GPUs by @mudler in https://github.com/mudler/LocalAI/pull/5385
* fix(transformers): pin protobuf by @mudler in https://github.com/mudler/LocalAI/pull/5421
* chore(scripts): allow to specify quants by @mudler in https://github.com/mudler/LocalAI/pull/5430
* fix(transformers): try to pin to working release by @mudler in https://github.com/mudler/LocalAI/pull/5426
* chore(model gallery): add nvidia_acereason-nemotron-14b by @mudler in https://github.com/mudler/LocalAI/pull/5463
* chore(deps): remove pin on transformers by @mudler in https://github.com/mudler/LocalAI/pull/5501
* feat(chatterbox): add new backend by @mudler in https://github.com/mudler/LocalAI/pull/5524
* fix(ci): try to add different mirrors to avoid 403 issues by @mudler in https://github.com/mudler/LocalAI/pull/5554
* Revert "fix(ci): try to add different mirrors to avoid 403 issues" by @mudler in https://github.com/mudler/LocalAI/pull/5555
* chore(deps): bump grpcio from 1.72.0 to 1.72.1 by @mudler in https://github.com/mudler/LocalAI/pull/5570
* fix(chatterbox): install only with cuda 12 by @mudler in https://github.com/mudler/LocalAI/pull/5573
* chore(deps): bump pytorch to 2.7 in vllm by @mudler in https://github.com/mudler/LocalAI/pull/5576
* fix(deps): pin grpcio by @mudler in https://github.com/mudler/LocalAI/pull/5621
* Improve Comments and Documentation for MixedMode and ParseJSON Functions by @leopardracer in https://github.com/mudler/LocalAI/pull/5626
* Fix Typos in Comments and Error Messages by @kilavvy in https://github.com/mudler/LocalAI/pull/5637
* docs: Update docs metadata headers so when mentioned on slack it doesn't say hugo by @halkeye in https://github.com/mudler/LocalAI/pull/5642
* Minor Documentation Updates: Clarified Comments in Python and Go Files by @vtjl10 in https://github.com/mudler/LocalAI/pull/5641
* chore: improve tests by @mudler in https://github.com/mudler/LocalAI/pull/5646
* Fix Typos and Improve Documentation Clarity by @zeevick10 in https://github.com/mudler/LocalAI/pull/5648
* chore(ci): use public runner for extra backends by @mudler in https://github.com/mudler/LocalAI/pull/5657
* chore: Add python3 to images by @mudler in https://github.com/mudler/LocalAI/pull/5660
* fix: add python symlink, use absolute python env path when running backends by @mudler in https://github.com/mudler/LocalAI/pull/5664
* chore(backend gallery): re-order and add description for vLLM by @mudler in https://github.com/mudler/LocalAI/pull/5676
* chore(backend gallery): add description for remaining backends by @mudler in https://github.com/mudler/LocalAI/pull/5679
* chore(ci): switch to public runners for base images by @mudler in https://github.com/mudler/LocalAI/pull/5680
* chore(ci): try to use public runners also for release builds by @mudler in https://github.com/mudler/LocalAI/pull/5681
* chore(ci): move also other jobs to public runner by @mudler in https://github.com/mudler/LocalAI/pull/5683
* Fix Typos in Documentation and Python Comments by @maximevtush in https://github.com/mudler/LocalAI/pull/5658
* Fix Typos and Improve Clarity in GPU Acceleration Documentation by @leopardracer in https://github.com/mudler/LocalAI/pull/5688

</details>

## New Contributors
* @omahs made their first contribution in https://github.com/mudler/LocalAI/pull/5376
* @TheDarkTrumpet made their first contribution in https://github.com/mudler/LocalAI/pull/5420
* @halkeye made their first contribution in https://github.com/mudler/LocalAI/pull/5589
* @leopardracer made their first contribution in https://github.com/mudler/LocalAI/pull/5626
* @kilavvy made their first contribution in https://github.com/mudler/LocalAI/pull/5637
* @vtjl10 made their first contribution in https://github.com/mudler/LocalAI/pull/5641
* @zeevick10 made their first contribution in https://github.com/mudler/LocalAI/pull/5648
* @maximevtush made their first contribution in https://github.com/mudler/LocalAI/pull/5658

**Full Changelog**: https://github.com/mudler/LocalAI/compare/v2.29.0...v3.0.0