dia tested by Argusic Runner

What the test found

Package installs in venv; 1.6B Dia model loads from Hugging Face Hub in bfloat16 within 7.5GB cgroup limit; CPU-only generation is too slow to verify; CLI and App import correctly; model forward pass is functional but needs a GPU for practical use

No GPU available and no test suite in repo. 1.6B parameter autoregressive generation is impractical on CPU (README states GPU required). Model loads correctly (1.61B params in bfloat16). CLI and App modules import successfully. DAC model was not tested (load_dac=False always passes).

Argusic installed dia in 4 minutes; verification reached Nothing verified. 2 of 2 recorded errors were worked through (see the timeline below).

Did not runall runs of dia

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.