LocalAI

v4.4.1 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 1mo Model Serving & MLOps

✓ No known CVEs patched

✓ 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

Summary

AI summary

Updates Other Changes, chore, and vllm across a mixed release.

Type	Severity	Summary	CVE
Feature	Medium	Streams LLM, TTS, and transcription pipeline stages for real-time processing. Streams LLM, TTS, and transcription pipeline stages for real-time processing. Source: llm_adapter@2026-06-11 Confidence: high	—
Bugfix	Medium	Restores compatibility with vLLM >= 0.22 by adjusting tokenizer import. Restores compatibility with vLLM >= 0.22 by adjusting tokenizer import. Source: llm_adapter@2026-06-11 Confidence: high	—

Full changelog

docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/10245
chore: :arrow_up: Update antirez/ds4 to 8384adf0f9fa0f3bb342dd925372de778b95b263 by @localai-bot in https://github.com/mudler/LocalAI/pull/10242
fix(vllm): restore compatibility with vLLM >= 0.22 (get_tokenizer moved to vllm.tokenizers) by @pos-ei-don in https://github.com/mudler/LocalAI/pull/10252
feat(realtime): stream the LLM / TTS / transcription pipeline stages by @localai-bot in https://github.com/mudler/LocalAI/pull/10176
docs: fix broken relref to realtime page by @localai-bot in https://github.com/mudler/LocalAI/pull/10255

@pos-ei-don made their first contribution in https://github.com/mudler/LocalAI/pull/10252

Full Changelog: https://github.com/mudler/LocalAI/compare/v4.4.0...v4.4.1

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

Track LocalAI

Get notified when new releases ship.

About LocalAI

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