NeAR / trellis /modules /sparse /attention

Commit History

  1. Force xformers CUTLASS attention on ZeroGPU

    fd70a38

  1. revert: remove sparse attention _linear inference-tensor clone hack⁠

    3f38e8f
  2. fix(sparse-attn): clone inference feats before Linear when grad is enabled⁠

    c7b33ad

  1. HF Space: drop ./vox2seq from requirements; vendored vox2seq_pytorch fallback⁠

    3715c3e
  2. restore: full Space tree + assets (recover from minimal force-push); keep ZeroGPU app.py⁠

    0d1388f