Misc. bug: llama-qwen2vl-cli: ignores --log* options

[l29ah]

Name and Version

‰ ./bin/llama-qwen2vl-cli --version version: 4391 (9ba399df) built with cc (Gentoo Hardened 14.2.1_p20241221 p6) 14.2.1 20241221 for x86_64-pc-linux-gnu

Operating systems

No response

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

No response

Problem description & steps to reproduce

Use --log-file /dev/null or --log-verbosity -100. Note lines like clip_model_load: model name: Qwen2-VL-7B-Instruct still being produced in stdout. There's seemingly no way to isolate the model output from the miscellaneous messages of llama.cpp.

First Bad Commit

No response

Relevant log output

No response