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

benchmarks: A0 gate — MLX TRELLIS.2 (Jourloy hybrid) BEATS MPS 216.6s vs 248.8s at 14x bake density; dark patches reproduce -> Metal texel sampling prime suspect

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
m3ultra 2026-07-19 12:46:16 +10:00
parent ace4be37ba
commit 0ac173d4fb
1 changed files with 25 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
BENCHMARKS.md
View File

@ -202,3 +202,28 @@ Verdict: keep (free, safe) but the paint UNet is GEMM-bound — fusion alone
is small. The bigger Hunyuan levers are Target 3 (MoE `.item()` sync-tax, is small. The bigger Hunyuan levers are Target 3 (MoE `.item()` sync-tax,
−4800 syncs/gen, unlocks whole-DiT compile) and Target 4 (manual→fused −4800 syncs/gen, unlocks whole-DiT compile) and Target 4 (manual→fused
SDPA in paint DINO). E2E flag-on-vs-off measurement pending after those. SDPA in paint DINO). E2E flag-on-vs-off measurement pending after those.
## 2026-07-19 — A0 GATE: first end-to-end MLX TRELLIS.2 (Jourloy PR#175 fork, m3ultra)
Same anatomy image, seed 42, 1024-cascade, tex 2048:
| path | wall (incl. load) | bake | peak mem | output |
|---|---|---|---|---|
| torch-MPS (trellis-mac) | 248.8 s | 19 s @191K faces | 20.8 GB | 21 MB GLB |
| **mlx-experimental (Jourloy)** | **216.6 s** | 83 s @**2.74M faces** | 75.4 GB | 131 MB PBR GLB |
**VERDICT: ADOPT — the MLX path BEAT the MPS baseline on wall-clock while
baking 14× the faces.** Key discovery: `mlx-experimental` is a HYBRID —
resolver log shows `Conv backend: flex_gemm; Attention: flex_gemm_sparse_attn`,
i.e. sparse ops still run pedronaugusto's Metal kernels; MLX runs the dense
stages. The feared naive-MLX-sparse-conv path never executes. Model load is
lazy/instant on the MLX side (vs 103 s torch load).
Quality: geometry excellent at full density; the DARK-PATCH texture defect
REPRODUCES on this second, independent pipeline — both paths share the
pedronaugusto mtldiffrast/BVH texel sampling. Culprit narrowed to those
shared Metal kernels OR the decoded tex attrs; the pure-Python KDTree bake
control (running) decides. fal renders clean with the same weights, so the
attrs are likely fine → Metal sampling is the prime suspect.
Caveat: 75 GB peak fits both Ultras but check m1 headroom under load.