6f887afb2b
The fp8_dynamic conv smoke probe only exercised Conv2d, so a torchao build whose Conv3d kernel path is missing or broken would pass the probe for a video VAE (HunyuanVideo-1.5), report it quantized, and crash at the first decode. The probe now runs per (device, conv ndim) and an explicit request must pass it for every conv dimensionality the target VAE contains; the auto ladder gate inspects the VAE the same way when one is provided. The video benchmark moved the fully dense pipeline to CUDA before applying the configured quant/optimisation levers, the reverse of the production loader (video.py quantizes before apply_memory_plan). Dense-oversized configs could OOM where the shipped quantized path loads fine, and load_peak_gb recorded the dense placement. The bench now builds on CPU, applies the levers, then places on CUDA and captures the load peak. |
||
|---|---|---|
| .. | ||
| assets | ||
| auth | ||
| core | ||
| hub | ||
| loggers | ||
| models | ||
| plugins | ||
| requirements | ||
| routes | ||
| state | ||
| storage | ||
| tests | ||
| utils | ||
| __init__.py | ||
| _platform_compat.py | ||
| cloudflare_tunnel.py | ||
| colab.py | ||
| main.py | ||
| run.py | ||
| startup_banner.py | ||