Add an Option<bool> use_gpu parameter to test_llm_model with the same
default-true semantics as load_llm_model. Hard-coding true triggered an
engine tear-down/rebuild when a parallel load_llm_model(use_gpu=false)
was in flight (LlmEngine::load_model triples on id+path+use_gpu) and
silently flipped the user's GPU mode underneath the test.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
