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

benchmarks: Hunyuan mlx-tune e2e 246s vs 260s baseline (~1.06x, texture-led)

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
m3ultra 2026-07-19 12:51:24 +10:00
parent 0476d1bc30
commit d488d87490
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
BENCHMARKS.md
View File

@ -227,3 +227,12 @@ 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.
## 2026-07-19 — Hunyuan mlx-tune e2e (T1+T3+T4, HY3D_MLX_COMPILE=1, m3ultra)
anatomy bench image, defaults (50 steps, octree 256): shape 146s + tex 101s
= **246s total, 17.5GB peak** vs recorded defaults baseline 260s (149+112).
≈ **1.06× e2e** — texture stage carries the win (112→101s = T4 fused DINO
+ T1 UNet compile); shape delta noise-level. Caveat: baseline row used a
different input image; same settings though. Next lever: Target 2
whole-DiT compile (unblocked by T3).