monster/modelbeast
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

benchmarks: KDTree control post-mortem — 5.85h bake + broken export; fast-rasterizer rewrite required

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
m3ultra 2026-07-19 15:52:26 +10:00
parent 142a0ac5da
commit 5d2a3f57e4
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
BENCHMARKS.md
View File

@ -270,3 +270,13 @@ All 8 fixtures captured at `trellis2-bench/parity_fixtures/` (cond_512/
1024, ss_coords, shape_slat, shape_dec, tex_slat, tex_voxels, mesh_final;
seed 42, 1024-cascade). Hook env needed: PYTORCH_ENABLE_MPS_FALLBACK=1
ATTN_BACKEND=sdpa SPARSE_ATTN_BACKEND=sdpa SPARSE_CONV_BACKEND=flex_gemm.
## 2026-07-19 — KDTree bake control: post-mortem (confirmatory run, superseded)
The TRELLIS2_FORCE_KDTREE control finally finished: **bake 21,063s (5.85h)**
and the exported GLB is GARBAGE geometry (mangled 395K-tri blob) — the
fork's KDTree export path has its own vertex-mapping bug on top of being
unusably slow (per-triangle Python rasterizer loop). Verdict unchanged —
the attrs-projection had already convicted the Metal texel-sampling — but
this rules out "just use the Python baker" as shipped: it needs the
fast-rasterizer rewrite + export fix (in progress as fast_bake_test.py).