ggml/llama.cpp releases: b11113

TL;DR

The ggml/llama.cpp project released a new version addressing an issue with log file handling on server processes. This update is important for improving the stability and security of the software, particularly when running on Apple Silicon hardware.

Detailed Summary

The ggml/llama.cpp project released a new update addressing issue #29212 by not passing log files to children processes. This update affects users of the macOS Apple Silicon (arm64) version and is documented on GitHub. The broader impact includes improved security and process management for macOS/iOS users, enhancing the overall stability and reliability of the software.

Key Points

• • server: do not pass log file to children (#29212)
• • Website: <https://llama.app>
• • Attestations: <https://github.com/ggml-org/llama.cpp/attestations/49344105>