3d482dcb88
_reset_step_cache looked up reset_stateful_hooks on the transformer, but on a diffusers CacheMixin transformer (Flux, QwenImage) that method lives only on the HookRegistry; the transformer-level entry point is _reset_stateful_cache. So with FBCache engaged on an image model the reset was a silent no-op, and the next generation reused the previous request's first-block residual: a tensor-shape mismatch (crash) when the resolution or batch changed, or stale cached output otherwise. Prefer _reset_stateful_cache and fall back to reset_stateful_hooks, matching the video backend. Update the tests to the real hook name. |
||
|---|---|---|
| .. | ||
| 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 | ||