fix(local-ai): update image docker.io/localai/localai v4.4.2 → v4.4.3 (#49114)
This PR contains the following updates:
| Package | Update | Change |
|---|---|---|
|
[docker.io/localai/localai](https://redirect.github.com/mudler/LocalAI)
| patch | `7d2d5ea` → `1aeb407` |
---
> [!WARNING]
> Some dependencies could not be looked up. Check the [Dependency
Dashboard](../issues/18710) 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>
###
[`v4.4.3`](https://redirect.github.com/mudler/LocalAI/releases/tag/v4.4.3)
[Compare
Source](https://redirect.github.com/mudler/LocalAI/compare/v4.4.2...v4.4.3)
<!-- Release notes generated using configuration in .github/release.yml
at master -->
#### What's Changed
##### Other Changes
- chore: :arrow\_up: Update CrispStrobe/CrispASR to
`d745bda4386ae0f9d1d2f23fff8ec95d76428221` by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10260](https://redirect.github.com/mudler/LocalAI/pull/10260)
- docs: :arrow\_up: update docs version mudler/LocalAI by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10259](https://redirect.github.com/mudler/LocalAI/pull/10259)
- chore: :arrow\_up: Update antirez/ds4 to
`d881f2a05e8ff6bec001315a36b794b4aa310173` by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10262](https://redirect.github.com/mudler/LocalAI/pull/10262)
- chore: :arrow\_up: Update mudler/parakeet.cpp to
`9db92be63179a27201d3b88d5d40c545b2ac48ae` by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10263](https://redirect.github.com/mudler/LocalAI/pull/10263)
- feat(react-ui): add Indonesian language support by
[@​dedyf5](https://redirect.github.com/dedyf5) in
[#​10266](https://redirect.github.com/mudler/LocalAI/pull/10266)
- chore: :arrow\_up: Update ggml-org/llama.cpp to
`4c6595503fe45d5a39f88d194e270f64c7424677` by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10261](https://redirect.github.com/mudler/LocalAI/pull/10261)
- feat(backend): locate-anything-cpp (open-vocabulary object detection
via ggml) by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10264](https://redirect.github.com/mudler/LocalAI/pull/10264)
- fix(router): production-ready request router + auto-size batch for
embedding/rerank by
[@​richiejp](https://redirect.github.com/richiejp) in
[#​10104](https://redirect.github.com/mudler/LocalAI/pull/10104)
- chore(model gallery): 🤖 add 1 new models via gallery agent by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10270](https://redirect.github.com/mudler/LocalAI/pull/10270)
- feat(parakeet-cpp): enable GGML\_CUDA\_GRAPHS in the cublas build by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10273](https://redirect.github.com/mudler/LocalAI/pull/10273)
- fix(darwin): publish sherpa-onnx and speaker-recognition images for
darwin/arm64 by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10275](https://redirect.github.com/mudler/LocalAI/pull/10275)
- fix(crispasr): write piper TTS WAV at the model's native sample rate
by [@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10277](https://redirect.github.com/mudler/LocalAI/pull/10277)
- feat(crispasr): bundle espeak-ng and add piper TTS voices to the
gallery by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10283](https://redirect.github.com/mudler/LocalAI/pull/10283)
- chore: :arrow\_up: Update mudler/parakeet.cpp to
`b8012f11e5269126eddb7f4fd02f891a2ccc29b0` by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10281](https://redirect.github.com/mudler/LocalAI/pull/10281)
- docs: :arrow\_up: update docs version mudler/LocalAI by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10279](https://redirect.github.com/mudler/LocalAI/pull/10279)
- fix(mlx): route vision-language models to the mlx-vlm backend by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10274](https://redirect.github.com/mudler/LocalAI/pull/10274)
- fix(darwin): fix vibevoice-cpp build linkage + fail-safe go backend
packaging by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10276](https://redirect.github.com/mudler/LocalAI/pull/10276)
- fix(agents): emit chat event timestamps in milliseconds
([#​9867](https://redirect.github.com/mudler/LocalAI/issues/9867))
by [@​aniruddh909](https://redirect.github.com/aniruddh909) in
[#​10243](https://redirect.github.com/mudler/LocalAI/pull/10243)
- fix(realtime): keep transcription model on a language-only
session.update by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10295](https://redirect.github.com/mudler/LocalAI/pull/10295)
- chore: :arrow\_up: Update mudler/locate-anything.cpp to
`92c1682da792c1e8a5dec91acc2be4b02c742ded` by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10282](https://redirect.github.com/mudler/LocalAI/pull/10282)
- fix(config): backend-gate the top\_k=40 sampler default
([#​6632](https://redirect.github.com/mudler/LocalAI/issues/6632))
by [@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10285](https://redirect.github.com/mudler/LocalAI/pull/10285)
- feat(gallery): add 60 piper TTS voices across 42 languages (Phase 2)
by [@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10296](https://redirect.github.com/mudler/LocalAI/pull/10296)
- fix(deps): bump cogito to fix MCP image-result panic
([#​10101](https://redirect.github.com/mudler/LocalAI/issues/10101))
by [@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10294](https://redirect.github.com/mudler/LocalAI/pull/10294)
- fix(neutts): pin torchaudio to match torch (fixes undefined symbol)
([#​9798](https://redirect.github.com/mudler/LocalAI/issues/9798))
by [@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10292](https://redirect.github.com/mudler/LocalAI/pull/10292)
- fix(gallery): make opus a meta backend for platform auto-selection
([#​9813](https://redirect.github.com/mudler/LocalAI/issues/9813))
by [@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10291](https://redirect.github.com/mudler/LocalAI/pull/10291)
- chore(model gallery): 🤖 add 1 new models via gallery agent by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10298](https://redirect.github.com/mudler/LocalAI/pull/10298)
- fix(gallery): correct meta-backend definitions for platform
auto-selection by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10299](https://redirect.github.com/mudler/LocalAI/pull/10299)
- chore(model gallery): 🤖 add 1 new models via gallery agent by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10302](https://redirect.github.com/mudler/LocalAI/pull/10302)
- ci(darwin): build the ds4 backend for darwin/arm64 (metal) by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10303](https://redirect.github.com/mudler/LocalAI/pull/10303)
- fix(react-ui): stop Talk pipeline overflow and center collapsed-rail
avatar by [@​localai-bot](https://redirect.github.com/localai-bot)
in
[#​10305](https://redirect.github.com/mudler/LocalAI/pull/10305)
- chore(model gallery): 🤖 add 1 new models via gallery agent by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10304](https://redirect.github.com/mudler/LocalAI/pull/10304)
- fix(react-ui): make agent chat timestamps format-agnostic
([#​9867](https://redirect.github.com/mudler/LocalAI/issues/9867))
by [@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10290](https://redirect.github.com/mudler/LocalAI/pull/10290)
- model: fix case-insensitive suffix matching and skip .bak files in
ListFilesInModelPath by
[@​pos-ei-don](https://redirect.github.com/pos-ei-don) in
[#​10306](https://redirect.github.com/mudler/LocalAI/pull/10306)
- fix(xsysinfo): container-aware total RAM detection (cgroup/lxcfs)
([#​8059](https://redirect.github.com/mudler/LocalAI/issues/8059))
by [@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10288](https://redirect.github.com/mudler/LocalAI/pull/10288)
- feat(distributed): declarative per-model scheduling via env/args by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10308](https://redirect.github.com/mudler/LocalAI/pull/10308)
- feat(sherpa-onnx): add Kokoro TTS + multilingual Piper voices by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10309](https://redirect.github.com/mudler/LocalAI/pull/10309)
- feat(omnivoice-cpp): add OmniVoice TTS backend (file + streaming,
voice cloning + voice design) by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10310](https://redirect.github.com/mudler/LocalAI/pull/10310)
- feat(i18n): add Korean (ko) translation by
[@​moduvoice](https://redirect.github.com/moduvoice) in
[#​10312](https://redirect.github.com/mudler/LocalAI/pull/10312)
- feat(qwen3-tts-cpp): migrate to ServeurpersoCom/qwentts.cpp
(streaming, speakers, voice design) by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10316](https://redirect.github.com/mudler/LocalAI/pull/10316)
- feat(realtime): gate realtime pipeline voice models behind voice
recognition by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10319](https://redirect.github.com/mudler/LocalAI/pull/10319)
- chore: :arrow\_up: Update vllm-project/vllm cu130 wheel to `0.23.0` by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10314](https://redirect.github.com/mudler/LocalAI/pull/10314)
- test(e2e): live-server voice-recognition gate test by
[@​localai-bot](https://redirect.github.com/localai-bot) in
[#​10324](https://redirect.github.com/mudler/LocalAI/pull/10324)
#### New Contributors
- [@​aniruddh909](https://redirect.github.com/aniruddh909) made
their first contribution in
[#​10243](https://redirect.github.com/mudler/LocalAI/pull/10243)
- [@​moduvoice](https://redirect.github.com/moduvoice) made their
first contribution in
[#​10312](https://redirect.github.com/mudler/LocalAI/pull/10312)
**Full Changelog**:
<https://github.com/mudler/LocalAI/compare/v4.4.2...v4.4.3>
</details>
---
### Configuration
📅 **Schedule**: (UTC)
- 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 this update
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:eyJjcmVhdGVkSW5WZXIiOiI0My4xMzAuMSIsInVwZGF0ZWRJblZlciI6IjQzLjEzMC4xIiwidGFyZ2V0QnJhbmNoIjoibWFzdGVyIiwibGFiZWxzIjpbImFwcC9sb2NhbC1haSIsImF1dG9tZXJnZSIsInJlbm92YXRlL2NvbnRhaW5lciIsInR5cGUvcGF0Y2giXX0=-->
