5df56c0804
train_precision_modes gates int8/fp8/mxfp8 on has_functional_torchao, and the Backend CI runner does not install torchao, so the three capability-gating tests collapsed to nf4/bf16/auto and failed. They exercise the CAPABILITY gate, not torchao presence: stub the probe functional alongside the CUDA capability patch. Validated with a torchao-blocked run (22 passed). |
||
|---|---|---|
| .. | ||
| 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 | ||