15a5e74434
Pixal3D refactored the container into a VarLenTensor base (feats + explicit slice-per-batch layout, no coords) with SparseTensor(VarLenTensor) adding coordinates. LATO.2 has only the combined class. Modelling the split here means one package serves both without either port adapting at every call site. Also exposes Pixal3D's cache spelling (get/register_spatial_cache) alongside LATO.2's (cache_get/cache_put). 13/13 tests unchanged.
9 lines
253 B
Plaintext
9 lines
253 B
Plaintext
Metadata-Version: 2.4
|
|
Name: trellis-sparse-mlx
|
|
Version: 0.1.0
|
|
Summary: MLX implementation of the TRELLIS-lineage sparse module (SubMConv3d et al) for Apple Silicon
|
|
License: MIT
|
|
Requires-Python: >=3.10
|
|
Requires-Dist: mlx>=0.20
|
|
Requires-Dist: numpy>=1.24
|