70cd436eb9
Extracted from lato.2_mrp_mlx. The same sparse module underlies LATO.2, Pixal3D and the rest of the TRELLIS.2 family, and all of them are blocked on Apple Silicon by the same single op - submanifold conv - so it belongs in one tested package rather than vendored per port. 13/13 tests: 7 for the conv against a hand-written reference (spconv is uninstallable here so there is no upstream oracle), 6 for the remaining layers against torch. SubMConv3d runs 13.8ms at 128^3/128ch on m3ultra, 5.9x faster than the obvious per-offset loop.
43 lines
881 B
JSON
43 lines
881 B
JSON
{
|
|
"machine": {
|
|
"host": "m3ultra",
|
|
"chip": "Apple M3 Ultra",
|
|
"ram_gb": 275,
|
|
"mlx": "0.32.0"
|
|
},
|
|
"occupancy": 0.1,
|
|
"rows": [
|
|
{
|
|
"res": 32,
|
|
"channels": 64,
|
|
"voxels": 3276,
|
|
"imap_ms": 3.659042005892843,
|
|
"conv_ms": 0.4588330048136413,
|
|
"mvox_s": 7.1398525512143
|
|
},
|
|
{
|
|
"res": 64,
|
|
"channels": 64,
|
|
"voxels": 26214,
|
|
"imap_ms": 28.264666034374386,
|
|
"conv_ms": 1.1872079921886325,
|
|
"mvox_s": 22.080376962148115
|
|
},
|
|
{
|
|
"res": 64,
|
|
"channels": 128,
|
|
"voxels": 26214,
|
|
"imap_ms": 28.218958992511034,
|
|
"conv_ms": 3.0656250310130417,
|
|
"mvox_s": 8.550947925727739
|
|
},
|
|
{
|
|
"res": 128,
|
|
"channels": 128,
|
|
"voxels": 209715,
|
|
"imap_ms": 232.5495420373045,
|
|
"conv_ms": 13.753084000200033,
|
|
"mvox_s": 15.2485798819341
|
|
}
|
|
]
|
|
} |