Skip to content

LocalAI

v4.2.2 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 22d Model Serving & MLOps
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agents ai api audio-generation decentralized distributed
+12 more
image-generation libp2p llama llm mamba mcp musicgen object-detection rerank stable-diffusion text-generation tts

ReleasePort's take

Light signal
editorial:auto 13d

LocalAI v4.2.2 fixes Vulkan VRAM parsing and Ollama /api/embed compatibility while patching GC and macOS gRPC issues. Standard dependency updates strengthen the stack.

Why it matters: Vulkan and Ollama compatibility fixes maintain ecosystem parity. GC race and macOS gRPC patches improve production reliability. Dependency updates (Anthropic SDK to 1.42.0, transformers ≥5.8.0) require testing in dev.

Summary

AI summary

Fixed parsing of Vulkan VRAM and added prompt alias for Ollama compatibility.

Changes in this release

Feature Medium

Expose new spec-decoding options in llama-cpp

Expose new spec-decoding options in llama-cpp

Source: llm_adapter@2026-05-21

Confidence: high

 —
Dependency Medium

Bump Anthropic SDK Go from 1.27.0 to 1.42.0

Bump Anthropic SDK Go from 1.27.0 to 1.42.0

Source: llm_adapter@2026-05-21

Confidence: high

 —
Dependency Medium

Update transformers minimum requirement to >=5.8.0

Update transformers minimum requirement to >=5.8.0

Source: llm_adapter@2026-05-21

Confidence: high

 —
Dependency Medium

Update charset-normalizer minimum requirement to >=3.4.7

Update charset-normalizer minimum requirement to >=3.4.7

Source: llm_adapter@2026-05-21

Confidence: high

 —
Dependency Medium

Bump npm and yarn dependencies

Bump npm and yarn dependencies

Source: llm_adapter@2026-05-21

Confidence: low

 —
Dependency Medium

Bump fsnotify from 1.9.0 to 1.10.1

Bump fsnotify from 1.9.0 to 1.10.1

Source: llm_adapter@2026-05-21

Confidence: low

 —
Dependency Medium

Bump edgevpn from 0.31.1 to 0.32.2

Bump edgevpn from 0.31.1 to 0.32.2

Source: llm_adapter@2026-05-21

Confidence: low

 —
Dependency Low

Update node from 25-slim to 26-slim

Update node from 25-slim to 26-slim

Source: granite4.1:30b@2026-05-23-audit

Confidence: low

 —
Dependency Low

Bump actions/upload-artifact from 4 to 7

Bump actions/upload-artifact from 4 to 7

Source: granite4.1:30b@2026-05-23-audit

Confidence: low

 —
Dependency Low

Bump actions/download-artifact from 4 to 8

Bump actions/download-artifact from 4 to 8

Source: granite4.1:30b@2026-05-23-audit

Confidence: low

 —
Dependency Low

Update npm and yarn dependencies across one directory with three updates

Update npm and yarn dependencies across one directory with three updates

Source: granite4.1:30b@2026-05-23-audit

Confidence: low

 —
Bugfix Medium

Parse Vulkan VRAM from text

Parse Vulkan VRAM from text

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Accept prompt alias on /api/embed for Ollama parity

Accept prompt alias on /api/embed for Ollama parity

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Close GC race condition and Darwin gRPC compatibility gaps

Close GC race condition and Darwin gRPC compatibility gaps

Source: llm_adapter@2026-05-21

Confidence: low

 —
Full changelog

What's Changed

Bug fixes :bug:

  • fix: parse vulkan VRAM from text by @eglia in https://github.com/mudler/LocalAI/pull/9669
  • fix(ollama): accept prompt alias on /api/embed for Ollama parity by @localai-bot in https://github.com/mudler/LocalAI/pull/9780

👒 Dependencies

  • chore(deps): bump node from 25-slim to 26-slim by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/9769
  • chore(deps): bump actions/upload-artifact from 4 to 7 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/9770
  • chore(deps): bump actions/download-artifact from 4 to 8 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/9771
  • chore(deps): bump github.com/anthropics/anthropic-sdk-go from 1.27.0 to 1.42.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/9772
  • chore(deps): bump github.com/onsi/gomega from 1.39.1 to 1.40.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/9774
  • chore(deps): update transformers requirement from >=5.0.0 to >=5.8.0 in /backend/python/transformers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/9775
  • chore(deps): bump github.com/fsnotify/fsnotify from 1.9.0 to 1.10.1 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/9778
  • chore(deps): update charset-normalizer requirement from >=3.4.0 to >=3.4.7 in /backend/python/vllm by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/9779
  • chore(deps): bump github.com/mudler/edgevpn from 0.31.1 to 0.32.2 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/9773
  • chore(deps): bump the npm_and_yarn group across 1 directory with 3 updates by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/9728

Other Changes

  • ci: close GC race + cascade-skip + darwin grpc gaps from v4.2.1 by @localai-bot in https://github.com/mudler/LocalAI/pull/9781
  • feat(llama-cpp): bump to 1ec7ba0c, adapt grpc-server, expose new spec-decoding options by @localai-bot in https://github.com/mudler/LocalAI/pull/9765

Full Changelog: https://github.com/mudler/LocalAI/compare/v4.2.1...v4.2.2

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track LocalAI

Get notified when new releases ship.

Sign up free

About LocalAI

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

All releases →

Related context

Beta — feedback welcome: [email protected]