Name and Version

llama.cpp/build/bin/llama-server --version
register_backend: registered backend Metal (1 devices)
register_device: registered device Metal (Apple M3 Pro)
register_backend: registered backend BLAS (1 devices)
register_device: registered device BLAS (Accelerate)
register_backend: registered backend CPU (1 devices)
register_device: registered device CPU (Apple M3 Pro)
version: 6324 (38ad381)
built with Apple clang version 17.0.0 (clang-1700.3.16.4) for arm64-apple-darwin25.0.0

Operating systems

Mac

Which llama.cpp modules do you know to be affected?

llama-server

Command line

llama-server --reranking -fa -ngl 99 -hf QuantFactory/Qwen3-Reranker-4B-GGUF:Q8_0 --host 127.0.0.1 --port 11881 -c 0 --log-timestamps --parallel 8 -t 8

Problem description & steps to reproduce

At startup, this will just immediately crash all running instances of Terminal. It's nothing very glamorous.

llama-server crash report.txt
Terminal.app crash report.txt

First Bad Commit

No response

Relevant log output