feat(local-ai): update image docker.io/localai/localai v3.11.0 → v3.12.0 (#45307)

This PR contains the following updates:

| Package | Update | Change |
|---|---|---|
|
[docker.io/localai/localai](https://redirect.github.com/mudler/LocalAI)
| minor | `89955bf` → `cf8354d` |
|
[docker.io/localai/localai](https://redirect.github.com/mudler/LocalAI)
| minor | `3a6f65a` → `4767bf4` |
|
[docker.io/localai/localai](https://redirect.github.com/mudler/LocalAI)
| minor | `5d585ef` → `3c3e62f` |

---

> [!WARNING]
> Some dependencies could not be looked up. Check the Dependency
Dashboard for more information.

Add the preset `:preserveSemverRanges` to your config if you don't want
to pin your dependencies.

---

### Release Notes

<details>
<summary>mudler/LocalAI (docker.io/localai/localai)</summary>

###
[`v3.12.0`](https://redirect.github.com/mudler/LocalAI/releases/tag/v3.12.0)

[Compare
Source](https://redirect.github.com/mudler/LocalAI/compare/v3.11.0...v3.12.0)

##### 🎉 LocalAI 3.12.0 Release! 🚀

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

LocalAI 3.12.0 is out!

| Feature | Summary |
| --------------------------- |
--------------------------------------------------------------------------------
|
| **Multi-modal Realtime** | Send text, images, and audio in real-time
conversations for richer interactions. |
| **Voxtral Backend** | New high-quality text-to-speech backend added. |
| **Multi-GPU Support** | Improved Diffusers performance with multiple
GPUs. |
| **Legacy CPU Optimization** | Enhanced compatibility for older
processors. |
| **UI Theme & Layout** | Improved UI theme (dark/light variants) and
navigation |
| **Realtime Stability** | Multiple fixes for audio, image, and model
handling. |
| **Logging Improvements** | Reduced excessive logs and optimized
processing. |

***

##### Local Stack Family

Liking LocalAI? LocalAI is part of an integrated suite of AI
infrastructure tools, you might also like:

- **[LocalAGI](https://redirect.github.com/mudler/LocalAGI)** - AI agent
orchestration platform with OpenAI Responses API compatibility and
advanced agentic capabilities
- **[LocalRecall](https://redirect.github.com/mudler/LocalRecall)** -
MCP/REST API knowledge base system providing persistent memory and
storage for AI agents
- 🆕 **[Cogito](https://redirect.github.com/mudler/cogito)** - Go library
for building intelligent, co-operative agentic software and LLM-powered
workflows, focusing on improving results for small, open source language
models that scales to any LLM. Powers LocalAGI and LocalAI MCP/Agentic
capabilities
- 🆕 **[Wiz](https://redirect.github.com/mudler/wiz)** - Terminal-based
AI agent accessible via Ctrl+Space keybinding. Portable, local-LLM
friendly shell assistant with TUI/CLI modes, tool execution with
approval, MCP protocol support, and multi-shell compatibility (zsh,
bash, fish)
- 🆕 **[SkillServer](https://redirect.github.com/mudler/skillserver)** -
Simple, centralized skills database for AI agents via MCP. Manages
skills as Markdown files with MCP server integration, web UI for
editing, Git synchronization, and full-text search capabilities

##### ❤️ Thank You

LocalAI is a true FOSS movement — built by contributors, powered by
community.

If you believe in privacy-first AI:

- ✅ **Star** the repo
- 💬 **Contribute** code, docs, or feedback
- 📣 **Share** with others

Your support keeps this stack alive.

***

##### ✅ Full Changelog

<details>
<summary>📋 Click to expand full changelog</summary>

##### What's Changed
##### Bug fixes 🐛
* security: validate URLs to prevent SSRF in content fetching endpoints
by
@&#8203;kolega-ai-d[https://github.com/mudler/LocalAI/pull/8476](https://redirect.github.com/mudler/LocalAI/pull/8476)l/8476
* fix(realtime): Use user provided voice and allow pipeline models to
have no backend by
@&#8203;richie[https://github.com/mudler/LocalAI/pull/8415](https://redirect.github.com/mudler/LocalAI/pull/8415)l/8415
* fix(realtime): Sampling and websocket locking by
@&#8203;richie[https://github.com/mudler/LocalAI/pull/8521](https://redirect.github.com/mudler/LocalAI/pull/8521)l/8521
* fix(realtime): Send proper image data to backend by
@&#8203;richie[https://github.com/mudler/LocalAI/pull/8547](https://redirect.github.com/mudler/LocalAI/pull/8547)l/8547
* fix: prevent excessive logging in capability detection by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8552](https://redirect.github.com/mudler/LocalAI/pull/8552)l/8552
* fix(voxcpm): pin setuptools by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8556](https://redirect.github.com/mudler/LocalAI/pull/8556)l/8556
* fix(llama-cpp): populate tensor_buft_override buffer so llama-cpp
properly performs fit calculations by
@&#8203;cvp[https://github.com/mudler/LocalAI/pull/8560](https://redirect.github.com/mudler/LocalAI/pull/8560)l/8560
* fix: pin neutts-air to known working commit by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8566](https://redirect.github.com/mudler/LocalAI/pull/8566)l/8566
* fix: improve watchdown logics by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8591](https://redirect.github.com/mudler/LocalAI/pull/8591)l/8591
* fix(llama-cpp): Pass parameters when using embedded template by
@&#8203;richie[https://github.com/mudler/LocalAI/pull/8590](https://redirect.github.com/mudler/LocalAI/pull/8590)l/8590
* fix(realtime): Better support for thinking models and setting model
parameters by
@&#8203;richie[https://github.com/mudler/LocalAI/pull/8595](https://redirect.github.com/mudler/LocalAI/pull/8595)l/8595
* fix(realtime): Limit buffer sizes to prevent DoS by
@&#8203;richie[https://github.com/mudler/LocalAI/pull/8596](https://redirect.github.com/mudler/LocalAI/pull/8596)l/8596
* fix(ui): improve view on mobile by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8598](https://redirect.github.com/mudler/LocalAI/pull/8598)l/8598
* fix(diffusers): sd_embed is not always available by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8602](https://redirect.github.com/mudler/LocalAI/pull/8602)l/8602
* fix: do not keep track model if not existing by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8603](https://redirect.github.com/mudler/LocalAI/pull/8603)l/8603

##### Exciting New Features 🎉
* feat(stablediffusion-ggml): Improve legacy CPU support for
stablediffusion-ggml backend by
@&#8203;cvp[https://github.com/mudler/LocalAI/pull/8461](https://redirect.github.com/mudler/LocalAI/pull/8461)l/8461
* feat(voxtral): add voxtral backend by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8451](https://redirect.github.com/mudler/LocalAI/pull/8451)l/8451
* feat(diffusers): add experimental support for sd_embed-style prompt
embedding by
@&#8203;cvp[https://github.com/mudler/LocalAI/pull/8504](https://redirect.github.com/mudler/LocalAI/pull/8504)l/8504
* chore: improve log levels verbosity by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8528](https://redirect.github.com/mudler/LocalAI/pull/8528)l/8528
* feat(realtime): Allow sending text, image and audio conversation
items" by
@&#8203;richie[https://github.com/mudler/LocalAI/pull/8524](https://redirect.github.com/mudler/LocalAI/pull/8524)l/8524
* chore: compute capabilities once by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8555](https://redirect.github.com/mudler/LocalAI/pull/8555)l/8555
* feat(ui): left navbar, dark/light theme by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8594](https://redirect.github.com/mudler/LocalAI/pull/8594)l/8594
* fix: multi-GPU support for Diffusers (Issue #&#8203;8575) by
@&#8203;loc[https://github.com/mudler/LocalAI/pull/8605](https://redirect.github.com/mudler/LocalAI/pull/8605)AI/pull/8605

##### 🧠 Models
* chore(model gallery): Add Ministral 3 family of models (aside from
base versions) by
@&#8203;ramp[https://github.com/mudler/LocalAI/pull/8467](https://redirect.github.com/mudler/LocalAI/pull/8467)l/8467
* chore(model gallery): add voxtral (which is only available in
development) by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8532](https://redirect.github.com/mudler/LocalAI/pull/8532)l/8532
* chore(model gallery): Add npc-llm-3-8b by
@&#8203;ramp[https://github.com/mudler/LocalAI/pull/8498](https://redirect.github.com/mudler/LocalAI/pull/8498)l/8498
* chore(model gallery): add nemo-asr by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8533](https://redirect.github.com/mudler/LocalAI/pull/8533)l/8533
* chore(model gallery): add voxcpm, whisperx, moonshine-tiny by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8534](https://redirect.github.com/mudler/LocalAI/pull/8534)l/8534
* chore(model gallery): add neutts by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8535](https://redirect.github.com/mudler/LocalAI/pull/8535)l/8535
* chore(model gallery): add vllm-omni models by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8536](https://redirect.github.com/mudler/LocalAI/pull/8536)l/8536
* chore(model-gallery): ⬆️ update checksum by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8540](https://redirect.github.com/mudler/LocalAI/pull/8540)l/8540
* feat(gallery): Add nanbeige4.1-3b by
@&#8203;richie[https://github.com/mudler/LocalAI/pull/8551](https://redirect.github.com/mudler/LocalAI/pull/8551)l/8551
* chore(model-gallery): ⬆️ update checksum by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8593](https://redirect.github.com/mudler/LocalAI/pull/8593)l/8593
* chore(model-gallery): ⬆️ update checksum by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8600](https://redirect.github.com/mudler/LocalAI/pull/8600)l/8600

##### 👒 Dependencies
* chore(deps): bump github.com/anthropics/anthropic-sdk-go from 1.20.0
to 1.22.0 by
@&#8203;dependabot[bo[https://github.com/mudler/LocalAI/pull/8482](https://redirect.github.com/mudler/LocalAI/pull/8482)l/8482
* chore(deps): bump github.com/jaypipes/ghw from 0.21.2 to 0.22.0 by
@&#8203;dependabot[bo[https://github.com/mudler/LocalAI/pull/8484](https://redirect.github.com/mudler/LocalAI/pull/8484)l/8484
* chore(deps): bump github.com/onsi/ginkgo/v2 from 2.28.0 to 2.28.1 by
@&#8203;dependabot[bo[https://github.com/mudler/LocalAI/pull/8483](https://redirect.github.com/mudler/LocalAI/pull/8483)l/8483
* chore(deps): bump github.com/alecthomas/kong from 1.13.0 to 1.14.0 by
@&#8203;dependabot[bo[https://github.com/mudler/LocalAI/pull/8481](https://redirect.github.com/mudler/LocalAI/pull/8481)l/8481
* chore(deps): bump github.com/openai/openai-go/v3 from 3.17.0 to 3.19.0
by
@&#8203;dependabot[bo[https://github.com/mudler/LocalAI/pull/8485](https://redirect.github.com/mudler/LocalAI/pull/8485)l/8485
* chore: bump cogito by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8568](https://redirect.github.com/mudler/LocalAI/pull/8568)l/8568
* fix(gallery): Use YAML v3 to avoid merging maps with incompatible keys
by
@&#8203;richie[https://github.com/mudler/LocalAI/pull/8580](https://redirect.github.com/mudler/LocalAI/pull/8580)l/8580
* chore(deps): bump google.golang.org/grpc from 1.78.0 to 1.79.1 by
@&#8203;dependabot[bo[https://github.com/mudler/LocalAI/pull/8583](https://redirect.github.com/mudler/LocalAI/pull/8583)l/8583
* chore(deps): bump github.com/jaypipes/ghw from 0.22.0 to 0.23.0 by
@&#8203;dependabot[bo[https://github.com/mudler/LocalAI/pull/8587](https://redirect.github.com/mudler/LocalAI/pull/8587)l/8587
* chore(deps): bump github.com/modelcontextprotocol/go-sdk from 1.2.0 to
1.3.0 by
@&#8203;dependabot[bo[https://github.com/mudler/LocalAI/pull/8585](https://redirect.github.com/mudler/LocalAI/pull/8585)l/8585
* chore(deps): bump cogito and add new options to the agent config by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8601](https://redirect.github.com/mudler/LocalAI/pull/8601)l/8601

##### Other Changes
* docs: ⬆️ update docs version mudler/LocalAI by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8462](https://redirect.github.com/mudler/LocalAI/pull/8462)l/8462
* docs: update model gallery documentation to reference main repository
by
@&#8203;veece[https://github.com/mudler/LocalAI/pull/8452](https://redirect.github.com/mudler/LocalAI/pull/8452)l/8452
* chore: ⬆️ Update ggml-org/whisper.cpp to
`4b23ff249e7f93137cb870b28fb27818e074c255` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8463](https://redirect.github.com/mudler/LocalAI/pull/8463)l/8463
* chore: ⬆️ Update ggml-org/llama.cpp to
`e06088da0fa86aa444409f38dff274904931c507` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8464](https://redirect.github.com/mudler/LocalAI/pull/8464)l/8464
* chore: ⬆️ Update antirez/voxtral.c to
`c9e8773a2042d67c637fc492c8a655c485354080` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8477](https://redirect.github.com/mudler/LocalAI/pull/8477)l/8477
* chore: ⬆️ Update ggml-org/llama.cpp to
`262364e31d1da43596fe84244fba44e94a0de64e` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8479](https://redirect.github.com/mudler/LocalAI/pull/8479)l/8479
* chore: ⬆️ Update ggml-org/whisper.cpp to
`764482c3175d9c3bc6089c1ec84df7d1b9537d83` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8478](https://redirect.github.com/mudler/LocalAI/pull/8478)l/8478
* chore: ⬆️ Update ggml-org/llama.cpp to
`57487a64c88c152ac72f3aea09bd1cc491b2f61e` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8499](https://redirect.github.com/mudler/LocalAI/pull/8499)l/8499
* chore: ⬆️ Update ggml-org/llama.cpp to
`4d3daf80f8834e0eb5148efc7610513f1e263653` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8513](https://redirect.github.com/mudler/LocalAI/pull/8513)l/8513
* chore: ⬆️ Update ggml-org/llama.cpp to
`338085c69e486b7155e5b03d7b5087e02c0e2528` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8538](https://redirect.github.com/mudler/LocalAI/pull/8538)l/8538
* fix: update moonshine API, add setuptools to voxcpm requirements by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8541](https://redirect.github.com/mudler/LocalAI/pull/8541)l/8541
* chore: ⬆️ Update ggml-org/llama.cpp to
`05a6f0e8946914918758db767f6eb04bc1e38507` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8553](https://redirect.github.com/mudler/LocalAI/pull/8553)l/8553
* chore: ⬆️ Update ggml-org/llama.cpp to
`01d8eaa28d57bfc6d06e30072085ed0ef12e06c5` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8567](https://redirect.github.com/mudler/LocalAI/pull/8567)l/8567
* chore: ⬆️ Update ggml-org/whisper.cpp to
`364c77f4ca2737e3287652e0e8a8c6dce3231bba` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8576](https://redirect.github.com/mudler/LocalAI/pull/8576)l/8576
* chore: ⬆️ Update antirez/voxtral.c to
`134d366c24d20c64b614a3dcc8bda2a6922d077d` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8578](https://redirect.github.com/mudler/LocalAI/pull/8578)l/8578
* chore: ⬆️ Update ggml-org/llama.cpp to
`27b93cbd157fc4ad94573a1fbc226d3e18ea1bb4` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8577](https://redirect.github.com/mudler/LocalAI/pull/8577)l/8577
* chore: ⬆️ Update ggml-org/llama.cpp to
`d612901116ab2066c7923372d4827032ff296bc4` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8588](https://redirect.github.com/mudler/LocalAI/pull/8588)l/8588
* chore: ⬆️ Update ggml-org/llama.cpp to
`2b089c77580d347767f440205103e4da8ec33d89` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8592](https://redirect.github.com/mudler/LocalAI/pull/8592)l/8592
* chore: ⬆️ Update ggml-org/llama.cpp to
`b55dcdef5dcd74dc75c4921090e928d43453c157` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8599](https://redirect.github.com/mudler/LocalAI/pull/8599)l/8599
* chore: ⬆️ Update ggml-org/whisper.cpp to
`21411d81ea736ed5d9cdea4df360d3c4b60a4adb` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8606](https://redirect.github.com/mudler/LocalAI/pull/8606)l/8606
* chore: ⬆️ Update ggml-org/llama.cpp to
`11c325c6e0666a30590cde390d5746a405e536b9` by
@&#8203;localai-b[https://github.com/mudler/LocalAI/pull/8607](https://redirect.github.com/mudler/LocalAI/pull/8607)l/8607
* chore(ui): improve navigation and buttons placement by
@&#8203;mudl[https://github.com/mudler/LocalAI/pull/8608](https://redirect.github.com/mudler/LocalAI/pull/8608)l/8608

</details>

##### New Contributors
* @&#8203;veeceey made their first
contributi[https://github.com/mudler/LocalAI/pull/8452](https://redirect.github.com/mudler/LocalAI/pull/8452)l/8452
* @&#8203;cvpcs made their first
contributi[https://github.com/mudler/LocalAI/pull/8461](https://redirect.github.com/mudler/LocalAI/pull/8461)l/8461
* @&#8203;kolega-ai-dev made their first
contributi[https://github.com/mudler/LocalAI/pull/8476](https://redirect.github.com/mudler/LocalAI/pull/8476)l/8476

**Full Changelog**:
<https://github.com/mudler/LocalAI/compare/v3.11.0...v3.12.0>

</details>

---

### Configuration

📅 **Schedule**: Branch creation - At any time (no schedule defined),
Automerge - At any time (no schedule defined).

🚦 **Automerge**: Enabled.

♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the
rebase/retry checkbox.

🔕 **Ignore**: Close this PR and you won't be reminded about these
updates again.

---

- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box

---

This PR has been generated by [Renovate
Bot](https://redirect.github.com/renovatebot/renovate).

<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0My4yNi4xIiwidXBkYXRlZEluVmVyIjoiNDMuMjYuMSIsInRhcmdldEJyYW5jaCI6Im1hc3RlciIsImxhYmVscyI6WyJhcHAvbG9jYWwtYWkiLCJhdXRvbWVyZ2UiLCJyZW5vdmF0ZS9jb250YWluZXIiLCJ0eXBlL21pbm9yIl19-->

charts/stable/local-ai/Chart.yaml

@@ -14,7 +14,7 @@ annotations:
   trueforge.org/min_helm_version: "3.14"
   trueforge.org/train: stable
 apiVersion: v2
-appVersion: 3.11.0
+appVersion: 3.12.0
 dependencies:
   - name: common
     version: 28.30.2
@@ -41,5 +41,5 @@ sources:
   - https://github.com/trueforge-org/truecharts/tree/master/charts/stable/local-ai
   - https://hub.docker.com/r/localai/localai
 type: application
-version: 16.52.1
+version: 16.55.0
 

charts/stable/local-ai/values.yaml

@@ -2,7 +2,7 @@
 image:
   repository: docker.io/localai/localai
   pullPolicy: IfNotPresent
-  tag: v3.11.0@sha256:5d585ef98040ca97b2d31c895d788930534ea4af47696f78b721a6eadc877bf1
+  tag: v3.12.0@sha256:3c3e62fa14db16e14dfd08d7864ecec7bb300010dd6f789f5cd1d7fcb40f1fe5
 ffmpegImage:
   repository: docker.io/localai/localai
   pullPolicy: IfNotPresent
@@ -26,7 +26,7 @@ cublasCuda11FfmpegImage:
 allInOneCuda12Image:
   repository: docker.io/localai/localai
   pullPolicy: IfNotPresent
-  tag: v3.11.0-aio-gpu-nvidia-cuda-12@sha256:3a6f65aac3057f7f49eb4bd3d69541e740fb3055755bfa1eb2a28a73147216a0
+  tag: v3.12.0-aio-gpu-nvidia-cuda-12@sha256:4767bf48bd3e74513e7c662a1da8571f9f050b145c83ea71db08d46b16424b75
 allInOneCuda11Image:
   repository: docker.io/localai/localai
   pullPolicy: IfNotPresent
@@ -34,7 +34,7 @@ allInOneCuda11Image:
 allInOneCpuImage:
   repository: docker.io/localai/localai
   pullPolicy: IfNotPresent
-  tag: v3.11.0-aio-cpu@sha256:89955bf3ecb8e72f8864baad3efc3034ec8b6c0d45102e50f6f47b11a4e6c155
+  tag: v3.12.0-aio-cpu@sha256:cf8354d174179f2a16cd79a2e82ab66380a9c84c9583f9447776f505e989744d
 securityContext:
   container:
     runAsNonRoot: false