localai 4.2.0

[BrewTestBot]

Created by brew bump

---

Created with brew bump-formula-pr.

Details

release notes

# 🎉 LocalAI 4.2.0 Release! 🚀

  

  
  

  


LocalAI 4.2.0 is out!
This release teaches LocalAI to see and hear. New /v1/voice/* and /v1/audio/diarization endpoints, a full face-recognition pipeline with antispoofing, word-level timestamps for faster-whisper, and a client-cancellable Whisper. There is also a drop-in Ollama API, video generation in stable-diffusion.ggml, a redesigned chat with i18n and admin-configurable branding, eleven new backends, an interactive model config editor with autocomplete, and a hardened distributed mode v2. vLLM finally hits feature parity with llama.cpp and gets tensor-parallel distributed workers.

📌 TL;DR



Feature
Summary




🎙️ Voice Recognition
New /v1/voice/*. Verify, identify, embed and analyze speakers.


👤 Face Recognition + Liveness
1:1 verify, 1:N identify, detect, analyze, embed, and reject spoofed photos.


🎬 Diarization
New /v1/audio/diarization endpoint, "who spoke when?" via sherpa-onnx + vibevoice.cpp.


🗣️ Better Transcriptions
Word-level timestamps, client-cancellable Whisper, segments + duration + language on the stream-done event.


🦙 Ollama API
Drop-in compatibility. Point your ollama client straight at LocalAI.


🎬 Video Generation
stable-diffusion.ggml now generates video (i2v, first-last-frame).


💬 Redesigned UI
Chat redesign, Nord palette, i18n (5 languages), admin-configurable branding.


✏️ Interactive Model Editor
Autocomplete-driven config editor in the UI.


📦 Universal Importer
Imports across most backends, not just llama.cpp.


🚦 Concurrency Groups
Per-model exclusive groups for safe backend loading.


🧪 11 New Backends
sglang, ik-llama-cpp, TurboQuant, sam.cpp, Kokoros, qwen3tts.cpp, tinygrad-multimodal, LocalVQE, vibevoice-cpp, insightface (liveness), voice-rec.


⚡ vLLM @ parity
Feature parity with llama.cpp + tensor-parallel distributed workers + full engine_args.


🛰️ Distributed v2
Hardened orchestrator, round-robin replicas, scoped Upgrade All, NATS install/upgrade split.




🚀 New Features & Major Enhancements
🎙️ Voice Recognition
LocalAI is now ears-on. New /v1/voice/* endpoints let you verify, identify, analyze and embed speakers, powered by a SpeechBrain + ONNX Python backend.

1:1 Verify, "is this the same speaker?"
1:N Identify, "who is talking, out of my enrolled users?"
Embeddings, voice fingerprints for your own pipelines
Analyze, age, gender, emotion attributes per segment


🔥 Pairs naturally with the new diarization endpoint for full speaker pipelines.


  

    
    voice.mp4
    
  

  



👤 Face Recognition & Antispoofing
A complete face-biometrics pipeline, built on InsightFace + ONNX.

1:1 Verify, match two faces
1:N Identify, resolve a face against an enrolled set
Detection & Analysis, find faces, extract attributes (age, gender, emotion, race)
Embeddings, facial fingerprints for your own stack
🆕 Antispoofing (liveness), reject spoofed photos and videos


✅ Samples never leave your machine. They go only to the running backend.


  

    
    face.mp4
    
  

  



🎬 Diarization & a smarter audio pipeline
Audio is a first-class citizen now.

/v1/audio/diarization, segments speech by speaker turn (sherpa-onnx + vibevoice.cpp)
Word-level timestamps for faster-whisper
Client cancellation for Whisper via the ggml abort_callback. Stop a transcription mid-flight and free the GPU.
Stream-done metadata on /v1/audio/transcriptions. segments, duration and language on the final event.
Audio transformations UI (LocalVQE), explore audio FX directly from the React UI
Transcription error visibility, handler errors land in the access log and on the client


🦙 Ollama drop-in API
Point your existing Ollama client at LocalAI. Everything keeps working. Another front door, same engine.
OLLAMA_HOST=http://localhost:8080 ollama run qwen3

🎬 Video Generation
The stable-diffusion.ggml backend now generates video, with curated gallery entries for Wan 2.1 FLF2V 14B 720P and Wan i2v 720p, plus a new stablediffusion-ggml-development meta backend to track the cutting edge.

🎨 React UI: total refresh
A massive UI cycle landed in 4.2:

💬 Chat redesign, cleaner layout, faster perceived latency, better message density
🎨 Editorial refresh with the Nord palette, calmer, more focused, dark-mode-first
🌍 Multilingual / i18n, English, Italiano, Español, Deutsch, 简体中文
🪪 Brandable instance, admin-configurable name, tagline, and assets (logo, favicon)
✏️ Interactive model config editor, autocomplete over known fields, live validation, automatic file-renaming on save
🧰 Backend management UX, revamped backend list with concrete versions
🛟 Better error UX, distributed backend management errors surface cleanly


💡 Self-host with your branding. The login page, sidebar, footer, and browser tab all pick up the instance name and logo.


  

    
    chat.mp4
    
  

  



  

    
    i18n.mp4
    
  

  



🔄 Backend & model lifecycle

Backend versioning with automatic upgrade detection
Pin models so they survive the reaper
On-demand toggle per model to control auto-load
Concurrency groups, per-model exclusive groups so heavy backends won't trample each other
Universal importer, single flow that imports across most backends, with clean multi-shard GGUF handling and dedicated importers for vibevoice-cpp and whisper.cpp HF repos


  

    
    importer.mp4
    
  

  



  

    
    model-editor.mp4
    
  

  



🧪 New Backends!



Backend
What it brings




sglang
High-throughput LLM serving + speculative decoding (EAGLE/EAGLE3/DFLASH/MTP)


ik-llama.cpp
ikawrakow's llama.cpp fork


TurboQuant
Quant-focused llama.cpp fork


sam.cpp
Segment Anything detection


Kokoros
Rust-native Kokoro TTS


qwen3tts.cpp
Qwen3 TTS


tinygrad-multimodal (experimental)
tinygrad-powered multimodal


vibevoice.cpp
Diarization-grade speech


LocalVQE
Audio transformations / FX


insightface
Face antispoofing


voice-rec
Speaker recognition / embeddings




⚡ vLLM at parity (and beyond)

vLLM parity with llama.cpp, same feature surface, same ergonomics
vLLM engine_args, the full AsyncEngineArgs exposed via a generic YAML map
Tensor-parallel distributed workers, fan a single model across nodes
CUDA 13 builds for vLLM, vLLM-omni and sglang
L4T arm64 (CUDA 13), vLLM/vLLM-omni/sglang variants for Jetson-class arm64
MLX backend refactored, shared helpers and enhanced functionality
llama.cpp split_mode for explicit multi-GPU placement
Speculative decoding wired through for llama.cpp, Gemma 4 thinking support added
Vision / mtmd marker propagated from the backend via ModelMetadata


🛰️ Distributed Mode v2
Distributed mode keeps maturing. This release was a hardening pass across the orchestration loop:

Orchestrator resilience, auto-upgrade routing, worker bind-wait, RAG-init crash, log-spam fixes
Round-robin across replicas of the same model
Upgrade All scoped to nodes that actually have the backend installed
NATS install / upgrade split, backend.upgrade no longer piggybacks on install
Cached-replica lookup honors NodeSelector, the reconciler no longer scales up empty backends
VRAM/RAM reporting correct on NVIDIA unified-memory hosts
Agent nodes, queue loops stop on teardown, dead-letter cap added
Autoscaling, load-model extracted from Route() and applied during autoscale


🔐 Auth & Security

Settings API, env-supplied ApiKeys are stripped before persisting (no accidental leaks)
grpc-server hardening, removed unsafe sprintf() in the C++ grpc server
OIDC, bumped go-oidc/v3 to 3.18.0
Security hardening pass across the codebase
AI coding assistants policy, LocalAI now follows the Linux kernel's DCO/attribution guidelines (Assisted-by: trailer, no AI co-authors)


🖥️ Hardware & deployment

CUDA 13 for vLLM, vLLM-omni, and sglang
NVIDIA L4T arm64 (CUDA 13) for Jetson-class boards
ROCm 7.x bumped to latest
gfx1151 (Strix Halo / Ryzen AI MAX) support, AMDGPU_TARGETS exposed as a build-arg
Intel GPU, latest oneapi-basekit (b70 support) across Intel images
arm64 CI, cpu-whisperx and cpu-faster-whisper now ship arm64 images
whisperx, ROCm/HIPBLAS target dropped (pinned to rocm6.4 wheels)


🛠️ Under the Hood

Better CLI errors with actionable guidance
golangci-lint baseline (new-from-merge-base) keeps drift in check
Coding-agent discoverability, new APIs let coding agents introspect and configure LocalAI
Autoparser, prefers backend-emitted chat deltas, correct logprob passthrough, strips partial reasoning tags during warm-up
Reasoning + tools, no more empty content from thinking models in retry loops
Streaming hygiene, deduped content, deduped tool calls, recovered reasoning, unique tool_call IDs in deferred flushes
HTTP, handler-error status now visible in the access log + transcription error surface
Backend monitor accepts model as a query parameter
Config loader, YAML backup files are ignored
GGUF thinking probe respects explicit reasoning config
Inference defaults refreshed from Unsloth
Embeddings on collection upload, dim changes handled gracefully
Python backends, JIT subprocesses use tempfile.gettempdir() instead of hardcoded /tmp
Draft model paths, relative paths now resolve against the models dir
whisper-cpp: implement streaming transcription and context cancellation


🐞 Notable fixes

Cascading user deletion on PostgreSQL, deleting a user removes all owned data
Importer emits all shards for multi-part GGUF models
Open Responses parses OpenAI-spec nested tool_choice and uses the correct setter
llama-cpp: server-chat.cpp included in grpc-server TU, common -> llama-common rename, turboquant common.h detection
ik-llama-cpp: adapted to common_grammar in sampling.h, patched clip.cpp for the new ggml_quantize_chunk signature
Kokoros: trait stubs (face_verify, face_analyze, audio_transcription_stream), CI publish
stable-diffusion.ggml: MP4 container forced in ffmpeg mux, new i2v options
Gallery: orphaned meta-backend uninstall, gemma-4 URIs, flux-kontext param overrides, Wan dedup, z-image-turbo load, Qwen3.5 typo override, tag-casing normalization
Streaming: content + tool-call dedup, reasoning recovery, unique tool-call IDs in deferred flush
Realtime: consume ChatDeltas when the C++ autoparser clears Response
Tool-calls: use SetFunctionCallNameString when forcing a specific tool
Faster-whisper: cast segment timestamps to int after multiplication
mlx-vlm: pinned to v0.4.4 to unblock CUDA builds
vLLM: dropped flash-attn wheel to avoid torch 2.10 ABI mismatch
Downloader: list supported URL schemes in DownloadFile errors
Backend: resolve relative draft_model paths against the models dir
CI: wire AMDGPU_TARGETS through the backend workflow, switch gallery-agent to sigs.k8s.io/yaml, recover rerankers + vllm-omni on aarch64, unbreak master CI for docs/kokoros/vibevoice-cpp ABI


🆕 Gallery additions

Wan 2.1 FLF2V 14B 720P (video)
Wan i2v 720p (image-to-video)
stablediffusion-ggml-development meta backend
chroma1-hd (diffusers)
Gemma 4 (+ mmproj)
EmbeddingGemma
Qwen 3.5, Qwen-ASR, OCR entries for llama.cpp
Qwen3-VL Reranker, Qwen3-VL Embedding (tagged)
A steady stream of automated gallery-agent model additions throughout the cycle 🤖


🚀 The Complete Local Stack for Privacy-First AI

  

    

      
        
        
LocalAI
      
    
    

      
The free, Open Source OpenAI alternative. Drop-in REST API compatible with OpenAI specs for local AI inferencing. No GPU required.
      
Link: https://github.com/mudler/LocalAI
    
  
  

    

      
         
         
LocalAGI
      
    
    

      
Local AI agent management platform. Drop-in for OpenAI's Responses API, with advanced agentic capabilities and a no-code UI.
      
Link: https://github.com/mudler/LocalAGI
    
  
  

    

      
         
         
LocalRecall
      
    
    

      
RESTful API and knowledge-base management providing persistent memory and storage for AI agents. Pairs with LocalAI and LocalAGI.
      
Link: https://github.com/mudler/LocalRecall
    
  


❤️ Thank You
LocalAI is a true FOSS movement, built by contributors, powered by community.
If you believe in privacy-first, self-hosted AI:

⭐ Star the repo
💬 Contribute code, docs, translations or feedback
📣 Share with others

Your support keeps this stack alive.

✅ Full Changelog

📋 Click to expand full changelog

What's Changed
Bug fixes :bug:

fix(autoscaling): extract load model from Route() and use as well when doing autoscale by @mudler in fix(autoscaling): extract load model from Route() and use as well when doing autoscale mudler/LocalAI#9270
fix(nodes): better detection if nodes goes down or model is not available by @mudler in fix(nodes): better detection if nodes goes down or model is not available mudler/LocalAI#9274
fix: try to add whisperx and faster-whisper for more variants by @mudler in fix: try to add whisperx and faster-whisper for more variants mudler/LocalAI#9278
fix: thinking models with tools returning empty content (reasoning-only retry loop) by @mudler in fix: thinking models with tools returning empty content (reasoning-only retry loop) mudler/LocalAI#9290
fix(streaming): deduplicate tool call emissions during streaming by @mudler in fix(streaming): deduplicate tool call emissions during streaming mudler/LocalAI#9292
fix(streaming): skip chat deltas for role-init elements to prevent first token duplication by @mudler in fix(streaming): skip chat deltas for role-init elements to prevent first token duplication mudler/LocalAI#9299
Fix load of z-image-turbo by @thelittlefireman in Fix load of z-image-turbo mudler/LocalAI#9264
fix(agents): handle embedding model dim changes on collection upload by @mudler in fix(agents): handle embedding model dim changes on collection upload mudler/LocalAI#9365
fix(gallery): correct gemma-4 model URIs returning 404 by @mvanhorn in fix(gallery): correct gemma-4 model URIs returning 404 mudler/LocalAI#9379
fix(ui): rename model config files on save to prevent duplicates by @mudler in fix(ui): rename model config files on save to prevent duplicates mudler/LocalAI#9388
fix(ci): switch gallery-agent to sigs.k8s.io/yaml by @mudler in fix(ci): switch gallery-agent to sigs.k8s.io/yaml mudler/LocalAI#9397
fix(llama-cpp): rename linked target common -> llama-common by @mudler in fix(llama-cpp): rename linked target common -> llama-common mudler/LocalAI#9408
fix(vision): propagate mtmd media marker from backend via ModelMetadata by @mudler in fix(vision): propagate mtmd media marker from backend via ModelMetadata mudler/LocalAI#9412
fix(turboquant): resolve common.h by detecting llama-common vs common target by @mudler in fix(turboquant): resolve common.h by detecting llama-common vs common target mudler/LocalAI#9413
fix(rocm): add gfx1151 support and expose AMDGPU_TARGETS build-arg by @keithmattix in fix(rocm): add gfx1151 support and expose AMDGPU_TARGETS build-arg mudler/LocalAI#9410
fix(kokoros): implement audio_transcription_stream trait stub by @mudler in fix(kokoros): implement audio_transcription_stream trait stub mudler/LocalAI#9422
fix(turboquant): drop ignore-eos patch, bump fork to b8967-627ebbc by @mudler in fix(turboquant): drop ignore-eos patch, bump fork to b8967-627ebbc mudler/LocalAI#9423
fix(distributed): stop queue loops on agent nodes + dead-letter cap by @mudler in fix(distributed): stop queue loops on agent nodes + dead-letter cap mudler/LocalAI#9433
fix(gallery): allow uninstalling orphaned meta backends + force reinstall by @mudler in fix(gallery): allow uninstalling orphaned meta backends + force reinstall mudler/LocalAI#9434
fix(stable-diffusion.ggml): force mp4 container in ffmpeg mux by @mudler in fix(stable-diffusion.ggml): force mp4 container in ffmpeg mux mudler/LocalAI#9435
fix(settings): strip env-supplied ApiKeys from the request before persisting by @SAY-5 in fix(settings): strip env-supplied ApiKeys from the request before persisting mudler/LocalAI#9438
fix(api): remove duplicate /api/traces endpoint that broke React UI by @pjbrzozowski in fix(api): remove duplicate /api/traces endpoint that broke React UI mudler/LocalAI#9427
fix(distributed): pass ExternalURI through NATS backend install by @russell in fix(distributed): pass ExternalURI through NATS backend install mudler/LocalAI#9446
fix(ci): wire AMDGPU_TARGETS through backend build workflow by @russell in fix(ci): wire AMDGPU_TARGETS through backend build workflow mudler/LocalAI#9445
fix(config): ignore yaml backup files in model loader by @leinasi2014 in fix(config): ignore yaml backup files in model loader mudler/LocalAI#9443
[gallery] Fix duplicate sha256 keys in Wan models by @sec171 in [gallery] Fix duplicate sha256 keys in Wan models mudler/LocalAI#9461
fix(tests): update InstallBackend call sites for new URI/Name/Alias params by @mudler in fix(tests): update InstallBackend call sites for new URI/Name/Alias params mudler/LocalAI#9467
Fix: Add model parameter to neutts-air gallery definition by @localai-bot in Fix: Add model parameter to neutts-air gallery definition mudler/LocalAI#8793
fix(gallery-agent): process blacklist command on recently-closed PRs by @mudler in fix(gallery-agent): process blacklist command on recently-closed PRs mudler/LocalAI#9473
Respect explicit reasoning config during GGUF thinking probe by @leinasi2014 in Respect explicit reasoning config during GGUF thinking probe mudler/LocalAI#9463
fix(streaming): dedupe content, recover reasoning, unique tool_call IDs in deferred flush by @mudler in fix(streaming): dedupe content, recover reasoning, unique tool_call IDs in deferred flush mudler/LocalAI#9470
fix(backend-monitor): accept model as a query parameter by @Dennisadira in fix(backend-monitor): accept model as a query parameter mudler/LocalAI#9411
fix(kokoros): Build and publish the backend images from CI/CD by @richiejp in fix(kokoros): Build and publish the backend images from CI/CD mudler/LocalAI#9487
fix: remove unsafe sprintf() in grpc-server.cpp by @orbisai0security in fix: remove unsafe sprintf() in grpc-server.cpp mudler/LocalAI#9486
fix(kokoros): implement face_verify and face_analyze trait stubs by @mudler in fix(kokoros): implement face_verify and face_analyze trait stubs mudler/LocalAI#9499
fix(ik-llama-cpp): adapt to common_grammar struct in sampling.h by @mudler in fix(ik-llama-cpp): adapt to common_grammar struct in sampling.h mudler/LocalAI#9512
fix(llama-cpp): include server-chat.cpp in grpc-server translation unit by @mudler in fix(llama-cpp): include server-chat.cpp in grpc-server translation unit mudler/LocalAI#9511
fix(importer): emit all shards for multi-part GGUF models by @mudler in fix(importer): emit all shards for multi-part GGUF models mudler/LocalAI#9513
fix(openresponses): parse OpenAI-spec nested tool_choice + use correct setter by @walcz-de in fix(openresponses): parse OpenAI-spec nested tool_choice + use correct setter mudler/LocalAI#9509
fix: use SetFunctionCallNameString when forcing a specific tool (3 sites) by @Anai-Guo in fix: use SetFunctionCallNameString when forcing a specific tool (3 sites) mudler/LocalAI#9526
fix(ik-llama-cpp): patch clip.cpp for new ggml_quantize_chunk signature by @mudler in fix(ik-llama-cpp): patch clip.cpp for new ggml_quantize_chunk signature mudler/LocalAI#9531
fix(realtime): consume ChatDeltas when C++ autoparser clears Response by @richiejp in fix(realtime): consume ChatDeltas when C++ autoparser clears Response mudler/LocalAI#9538
fix: add hipblaslt library by @eglia in fix: add hipblaslt library mudler/LocalAI#9541
fix(distributed): correct VRAM/RAM reporting on NVIDIA unified-memory hosts by @mudler in fix(distributed): correct VRAM/RAM reporting on NVIDIA unified-memory hosts mudler/LocalAI#9545
fix(vllm): drop flash-attn wheel to avoid torch 2.10 ABI mismatch by @richiejp in fix(vllm): drop flash-attn wheel to avoid torch 2.10 ABI mismatch mudler/LocalAI#9557
fix(mlx-vlm): pin upstream to v0.4.4 to unblock CUDA builds by @mudler in fix(mlx-vlm): pin upstream to v0.4.4 to unblock CUDA builds mudler/LocalAI#9568
fix(gallery): normalize inconsistent tag casing/plurals across gallery models by @Anai-Guo in fix(gallery): normalize inconsistent tag casing/plurals across gallery models mudler/LocalAI#9574
fix(gallery): correct Qwen3.5 typo in qwen3.5-27b-claude-4.6 model override (closes #9362) by @Anai-Guo in fix(gallery): correct Qwen3.5 typo in qwen3.5-27b-claude-4.6 model override (closes #9362) mudler/LocalAI#9580
fix(diffusers): drop compel from requirements to unblock pip resolver by @mudler in fix(diffusers): drop compel from requirements to unblock pip resolver mudler/LocalAI#9632
fix(ci): fix AMDGPU_TARGETS empty-string bypass in hipblas builds by @russell in fix(ci): fix AMDGPU_TARGETS empty-string bypass in hipblas builds mudler/LocalAI#9626
fix(distributed): honor NodeSelector in cached-replica lookup, stop empty-backend reconciler scaleups by @localai-bot in fix(distributed): honor NodeSelector in cached-replica lookup, stop empty-backend reconciler scaleups mudler/LocalAI#9652
fix(distributed): orchestrator resilience — auto-upgrade routing, worker bind-wait, RAG-init crash, log spam by @localai-bot in fix(distributed): orchestrator resilience — auto-upgrade routing, worker bind-wait, RAG-init crash, log spam mudler/LocalAI#9657
fix(faster-whisper): cast segment timestamps to int after multiplication by @arteven in fix(faster-whisper): cast segment timestamps to int after multiplication mudler/LocalAI#9674
fix(python-backend): make JIT subprocesses work on hosts of any size by @richiejp in fix(python-backend): make JIT subprocesses work on hosts of any size mudler/LocalAI#9679
fix(distributed): scope Upgrade All to nodes that have the backend installed by @mudler in fix(distributed): scope Upgrade All to nodes that have the backend installed mudler/LocalAI#9678
fix(backend): resolve relative draft_model paths against the models dir by @localai-bot in fix(backend): resolve relative draft_model paths against the models dir mudler/LocalAI#9680
fix: unbreak master CI (docs, kokoros, vibevoice-cpp ABI) by @localai-bot in fix: unbreak master CI (docs, kokoros, vibevoice-cpp ABI) mudler/LocalAI#9682
fix(ci): unbreak rerankers (torch bump) and vllm-omni on aarch64 by @localai-bot in fix(ci): unbreak rerankers (torch bump) and vllm-omni on aarch64 mudler/LocalAI#9688
fix(distributed): round-robin replicas of the same model by @localai-bot in fix(distributed): round-robin replicas of the same model mudler/LocalAI#9695
fix(downloader): list supported URL schemes in DownloadFile error by @Anai-Guo in fix(downloader): list supported URL schemes in DownloadFile error mudler/LocalAI#9689
fix(auth): cascade user deletion across all owned data on PostgreSQL by @localai-bot in fix(auth): cascade user deletion across all owned data on PostgreSQL mudler/LocalAI#9702
fix(http): make handler-error status visible in access log + transcription errors by @localai-bot in fix(http): make handler-error status visible in access log + transcription errors mudler/LocalAI#9707
fix(distributed): make backend upgrade actually re-install on workers by @localai-bot in fix(distributed): make backend upgrade actually re-install on workers mudler/LocalAI#9708
fix(distributed): split NATS backend.upgrade off install + dedup loads by @localai-bot in fix(distributed): split NATS backend.upgrade off install + dedup loads mudler/LocalAI#9717
fix(gallery): keep auto-upgrade off non-dev backends when -development is installed by @mudler in fix(gallery): keep auto-upgrade off non-dev backends when -development is installed mudler/LocalAI#9736

Exciting New Features 🎉

feat(ui): Interactive model config editor with autocomplete by @richiejp in feat(ui): Interactive model config editor with autocomplete mudler/LocalAI#9149
feat: track files being staged by @mudler in feat: track files being staged mudler/LocalAI#9275
feat: Add Kokoros backend by @richiejp in feat: Add Kokoros backend mudler/LocalAI#9212
feat(api): add ollama compatibility by @mudler in feat(api): add ollama compatibility mudler/LocalAI#9284
feat(sam.cpp): add sam.cpp detection backend by @mudler in feat(sam.cpp): add sam.cpp detection backend mudler/LocalAI#9288
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9300
chore(qwen3-asr): pass prompt as context to transcribe by @mudler in chore(qwen3-asr): pass prompt as context to transcribe mudler/LocalAI#9301
feat: Add toggle mechanism to enable/disable models from loading on demand by @neurocis in feat: Add toggle mechanism to enable/disable models from loading on demand mudler/LocalAI#9304
feat: allow to pin models and skip from reaping by @mudler in feat: allow to pin models and skip from reaping mudler/LocalAI#9309
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9310
feat: backend versioning, upgrade detection and auto-upgrade by @mudler in feat: backend versioning, upgrade detection and auto-upgrade mudler/LocalAI#9315
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9318
feat(qwen3tts.cpp): add new backend by @mudler in feat(qwen3tts.cpp): add new backend mudler/LocalAI#9316
feat(ux): backend management enhancement by @mudler in feat(ux): backend management enhancement mudler/LocalAI#9325
feat(rocm): bump to 7.x by @mudler in feat(rocm): bump to 7.x mudler/LocalAI#9323
feat(backends): add ik-llama-cpp by @mudler in feat(backends): add ik-llama-cpp mudler/LocalAI#9326
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9329
feat(vllm): parity with llama.cpp backend by @mudler in feat(vllm): parity with llama.cpp backend mudler/LocalAI#9328
feat: refactor shared helpers and enhance MLX backend functionality by @mudler in feat: refactor shared helpers and enhance MLX backend functionality mudler/LocalAI#9335
feat: wire transcription for llama.cpp, add streaming support by @mudler in feat: wire transcription for llama.cpp, add streaming support mudler/LocalAI#9353
feat(backend): add turboquant llama.cpp-fork backend by @mudler in feat(backend): add turboquant llama.cpp-fork backend mudler/LocalAI#9355
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9356
feat(backend): add tinygrad multimodal backend (experimental) by @mudler in feat(backend): add tinygrad multimodal backend (experimental) mudler/LocalAI#9364
feat(backends): add sglang by @mudler in feat(backends): add sglang mudler/LocalAI#9359
refactor(tinygrad): reuse tinygrad.apps.llm instead of vendored Transformer by @mudler in refactor(tinygrad): reuse tinygrad.apps.llm instead of vendored Transformer mudler/LocalAI#9380
feat(stable-diffusion.ggml): add support for video generation by @mudler in feat(stable-diffusion.ggml): add support for video generation mudler/LocalAI#9420
feat(distributed): sync state with frontends, better backend management reporting by @mudler in feat(distributed): sync state with frontends, better backend management reporting mudler/LocalAI#9426
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9431
feat(gallery): add Wan 2.1 FLF2V 14B 720P by @mudler in feat(gallery): add Wan 2.1 FLF2V 14B 720P mudler/LocalAI#9440
feat(gallery): add wan i2v 720p by @mudler in feat(gallery): add wan i2v 720p mudler/LocalAI#9457
feat: improve CLI error messages with actionable guidance by @localai-bot in feat: improve CLI error messages with actionable guidance mudler/LocalAI#8880
chore(whisperx): drop ROCm/hipblas build target by @mudler in chore(whisperx): drop ROCm/hipblas build target mudler/LocalAI#9474
feat(face-recognition): add insightface/onnx backend for 1:1 verify, 1:N identify, embedding, detection, analysis by @mudler in feat(face-recognition): add insightface/onnx backend for 1:1 verify, 1:N identify, embedding, detection, analysis mudler/LocalAI#9480
feat(importer): expand importer flow to almost all backends by @mudler in feat(importer): expand importer flow to almost all backends mudler/LocalAI#9466
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9498
feat: voice recognition by @mudler in feat: voice recognition mudler/LocalAI#9500
feat(insightface): add antispoofing (liveness) detection by @mudler in feat(insightface): add antispoofing (liveness) detection mudler/LocalAI#9515
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9518
feat: add biometrics UI by @mudler in feat: add biometrics UI mudler/LocalAI#9524
feat: Add Sherpa ONNX backend for ASR and TTS by @richiejp in feat: Add Sherpa ONNX backend for ASR and TTS mudler/LocalAI#8523
[intel GPU support] Use latest oneapi-basekit image for Intel images to support b70 by @arbrick in [intel GPU support] Use latest oneapi-basekit image for Intel images to support b70 mudler/LocalAI#9543
feat(react-ui): editorial refresh with Nord palette and polished primitives by @mudler in feat(react-ui): editorial refresh with Nord palette and polished primitives mudler/LocalAI#9550
feat: surface distributed backend management errors by @mudler in feat: surface distributed backend management errors mudler/LocalAI#9552
feat(backends): add CUDA 13 + L4T arm64 CUDA 13 variants for vllm/vllm-omni/sglang by @mudler in feat(backends): add CUDA 13 + L4T arm64 CUDA 13 variants for vllm/vllm-omni/sglang mudler/LocalAI#9553
feat(llama-cpp): expose split_mode option for multi-GPU placement by @mudler in feat(llama-cpp): expose split_mode option for multi-GPU placement mudler/LocalAI#9560
ci(backends): build cpu-whisperx and cpu-faster-whisper for linux/arm64 by @mudler in ci(backends): build cpu-whisperx and cpu-faster-whisper for linux/arm64 mudler/LocalAI#9573
[intel GPU support] Use latest oneapi-basekit image for Intel images to support b70 (in more places this time) by @arbrick in [intel GPU support] Use latest oneapi-basekit image for Intel images to support b70 (in more places this time) mudler/LocalAI#9578
feat: Log backend exit code by @richiejp in feat: Log backend exit code mudler/LocalAI#9581
feat(distributed): support multiple replicas of one model on the same node by @mudler in feat(distributed): support multiple replicas of one model on the same node mudler/LocalAI#9583
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9587
feat: localai assistant chat modality by @mudler in feat: localai assistant chat modality mudler/LocalAI#9602
chore: add golangci-lint with new-from-merge-base baseline by @richiejp in chore: add golangci-lint with new-from-merge-base baseline mudler/LocalAI#9603
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9607
feat(vllm): expose AsyncEngineArgs via generic engine_args YAML map by @richiejp in feat(vllm): expose AsyncEngineArgs via generic engine_args YAML map mudler/LocalAI#9563
feat(vibevoice-cpp): add purego TTS+ASR backend by @mudler in feat(vibevoice-cpp): add purego TTS+ASR backend mudler/LocalAI#9610
feat: react chat redesign by @mudler in feat: react chat redesign mudler/LocalAI#9616
feat(llama-cpp): bump to d775992 and adapt to spec params refactor by @mudler in feat(llama-cpp): bump to d775992 and adapt to spec params refactor mudler/LocalAI#9618
feat(backends/python): use tempfile.gettempdir() instead of hardcoded /tmp by @Anai-Guo in feat(backends/python): use tempfile.gettempdir() instead of hardcoded /tmp mudler/LocalAI#9629
feat(importers): whisper.cpp HF repos pick a quant + nest under whisper/models by @mudler in feat(importers): whisper.cpp HF repos pick a quant + nest under whisper/models mudler/LocalAI#9630
feat(branding): admin-configurable instance name, tagline, and assets by @mudler in feat(branding): admin-configurable instance name, tagline, and assets mudler/LocalAI#9635
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9643
feat(react-ui): add multilingual (i18n) support by @mudler in feat(react-ui): add multilingual (i18n) support mudler/LocalAI#9642
feat(ci): allow routing apt traffic through an alternate Ubuntu mirror by @mudler in feat(ci): allow routing apt traffic through an alternate Ubuntu mirror mudler/LocalAI#9650
feat: add LocalVQE backend and audio transformations UI by @richiejp in feat: add LocalVQE backend and audio transformations UI mudler/LocalAI#9640
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9660
feat(concurrency-groups): per-model exclusive groups for backend loading by @mudler in feat(concurrency-groups): per-model exclusive groups for backend loading mudler/LocalAI#9662
feat(api): add /v1/audio/diarization endpoint with sherpa-onnx + vibevoice.cpp by @mudler in feat(api): add /v1/audio/diarization endpoint with sherpa-onnx + vibevoice.cpp mudler/LocalAI#9654
feat(vllm, distributed): tensor parallel distributed workers by @richiejp in feat(vllm, distributed): tensor parallel distributed workers mudler/LocalAI#9612
feat: support word-level timestamps for faster-whisper by @eglia in feat: support word-level timestamps for faster-whisper mudler/LocalAI#9621
feat(importers): add vibevoice-cpp importer for GGUF bundles by @localai-bot in feat(importers): add vibevoice-cpp importer for GGUF bundles mudler/LocalAI#9685
feat(gallery): Speed up load times and clean gallery entries by @richiejp in feat(gallery): Speed up load times and clean gallery entries mudler/LocalAI#9211
feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger mudler/LocalAI#9699
feat(sglang): wire engine_args, add cuda13 build, ship MTP gallery demos by @richiejp in feat(sglang): wire engine_args, add cuda13 build, ship MTP gallery demos mudler/LocalAI#9686
feat(api/transcription): include segments + duration + language on stream done event by @localai-bot in feat(api/transcription): include segments + duration + language on stream done event mudler/LocalAI#9709
feat(whisper): honor client cancellation via ggml abort_callback by @localai-bot in feat(whisper): honor client cancellation via ggml abort_callback mudler/LocalAI#9710
chore: Security hardening by @richiejp in chore: Security hardening mudler/LocalAI#9719
ci: phase 1-3 of GHA free tier migration (path filter, multi-arch split prep, /mnt disk relief) by...

View the full release notes at https://github.com/mudler/LocalAI/releases/tag/v4.2.0.

---

[github-actions]

🤖 An automated task has requested bottles to be published to this PR.

Caution

Please do not push to this PR branch before the bottle commits have been pushed, as this results in a state that is difficult to recover from. If you need to resolve a merge conflict, please use a merge commit. Do not force-push to this PR branch.