Fix real OOM: 4-D SDPA layout; cu130 is ZeroGPU-native, drop cu128 cruft

Revert cu130 forcing; use ZeroGPU-native cu128 torch + pip cu128 nvcc

Move torch stack to 2.11.0 to resolve xformers conflict

Force cu130 torch at startup before importing torch

Make cu130 the primary pip index, keep torch pin bare

Pin torch/torchvision to explicit +cu130 local version

Move torch stack to cu130 to match ZeroGPU CUDA 13.0 toolkit

Bump torch to 2.8.0 for ZeroGPU compatibility

Initial commit

Initial commit

Initial commit

Initial commit

Initial commit

Initial commit

Initial commit

Initial commit

Initial commit

Initial commit

Initial commit