v4.4.2

DioxusLabs/dioxusv4.4.2Jun 11, 2026by mudler

AI Summary

A maintenance release addressing dependency updates and specific bug fixes for VLLM and CUDA environments to improve stability.

Key Highlights

  • Dependency updates for llama.cpp and CrispASR.
  • Fix for VLLM tool call function argument parsing.
  • Fix for CUDA installation to include nvrtc-dev alongside other dev packages.

New Features

  • VLLM tool call parsing fix
  • CUDA nvrtc-dev installation fix

Full Release Notes

<!-- Release notes generated using configuration in .github/release.yml at master -->

## What's Changed
### Other Changes
* chore: :arrow_up: Update ggml-org/llama.cpp to `ac4cddeb0dbd778f650bf568f6f08344a06abe3a` by @localai-bot in https://github.com/mudler/LocalAI/pull/10239
* chore: :arrow_up: Update CrispStrobe/CrispASR to `4b27392ffd0991a857594652cbb8b57e585bcd7b` by @localai-bot in https://github.com/mudler/LocalAI/pull/10241
* fix(vllm): parse tool_call function arguments before applying the chat template by @pos-ei-don in https://github.com/mudler/LocalAI/pull/10256
* fix(cuda): install cuda-nvrtc-dev alongside the other CUDA dev packages by @pos-ei-don in https://github.com/mudler/LocalAI/pull/10257


**Full Changelog**: https://github.com/mudler/LocalAI/compare/v4.4.1...v4.4.2