93e31f9f80
SparseDiTAttention / SparseProjectAttention / ModulatedSparseTransformerCrossBlock - the sparse counterparts of the dense DiT pieces, attending within each batch item. The modulation needs care: it is per batch item ([B, 6C]) while features are a flat [N, C] stack, so each row must pick up its own item's shift/scale/gate. Broadcasting would silently apply item 0's modulation to everything when B == 1. Verified end to end: slat_flow matches upstream at correlation 1.00000000.
56 lines
2.0 KiB
Python
56 lines
2.0 KiB
Python
"""MLX implementation of the TRELLIS-lineage sparse module.
|
|
|
|
Microsoft's TRELLIS.2 sparse stack has been inherited, near-verbatim, by a growing
|
|
family of 3D generation models — LATO.2 and TencentARC's Pixal3D among them. All of
|
|
them hard-require spconv or torchsparse, neither of which has a Metal build, and that
|
|
single dependency is what keeps the whole lineage off Apple Silicon.
|
|
|
|
The blocker is one operation: submanifold 3x3x3 convolution. Every SparseConv3d in
|
|
these models is constructed `stride=1, padding=None`, which spconv dispatches to
|
|
SubMConv3d. Implement that in MLX and the rest is ordinary linear/norm/attention work.
|
|
|
|
Packaged separately from any one model so each port depends on a tested core rather
|
|
than vendoring its own copy.
|
|
"""
|
|
|
|
from .conv import SubMConv3d, build_indice_map
|
|
from .dit import (
|
|
ProjectAttention,
|
|
DiTAttention,
|
|
ModulatedTransformerCrossBlock,
|
|
MultiHeadRMSNorm,
|
|
TimestepEmbedder,
|
|
apply_rope,
|
|
rope_phases_from_coords,
|
|
SparseDiTAttention,
|
|
SparseProjectAttention,
|
|
ModulatedSparseTransformerCrossBlock,
|
|
)
|
|
from .tensor import SparseTensor, VarLenTensor, downsample, subdivide, upsample
|
|
from .ops import (
|
|
LayerNorm32,
|
|
SparseFeedForwardNet,
|
|
SparseGELU,
|
|
SparseGroupNorm32,
|
|
SparseLinear,
|
|
SparseMultiHeadAttention,
|
|
SparseResBlock,
|
|
SparseSiLU,
|
|
SparseTransformerBlock,
|
|
SparseTransformerCrossBlock,
|
|
)
|
|
|
|
__all__ = [
|
|
"SparseTensor", "VarLenTensor", "subdivide", "downsample", "upsample",
|
|
"SubMConv3d", "build_indice_map",
|
|
"SparseLinear", "LayerNorm32", "SparseGroupNorm32", "SparseSiLU", "SparseGELU",
|
|
"SparseResBlock", "SparseFeedForwardNet", "SparseMultiHeadAttention",
|
|
"SparseTransformerBlock", "SparseTransformerCrossBlock",
|
|
# DiT / flow-model pieces
|
|
"MultiHeadRMSNorm", "apply_rope", "rope_phases_from_coords", "TimestepEmbedder", "DiTAttention",
|
|
"ModulatedTransformerCrossBlock", "ProjectAttention",
|
|
"SparseDiTAttention", "SparseProjectAttention",
|
|
"ModulatedSparseTransformerCrossBlock",
|
|
]
|
|
__version__ = "0.1.0"
|