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

rung 3 final: M1 Ultra validated — 181.5s / 17.2GB, both Ultras now run optimized MLX TRELLIS.2

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
m3ultra 2026-07-20 04:16:29 +10:00
parent 95aa214b1e
commit eb3862bb8a
2 changed files with 32 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
BENCHMARKS.md
View File

@ -432,3 +432,19 @@ Honest negatives (documented so nobody re-chases them):
Env knobs (all default-sane): TRELLIS2_MLX_SAMPLER=0 (revert sampler),
TRELLIS2_MLX_COMPILE=1, TRELLIS2_METAL_SPCONV=1.
M1 Ultra validation: in flight (26.5GB peak fits with 100GB headroom).
### Rung-3 addendum — M1 Ultra validated (2026-07-20)
| box | e2e wall | peak mem |
|---|---|---|
| m3ultra | 71.96 s | 26.5 GB |
| **m1ultra** | **181.5 s** | **17.2 GB** |
The M1 Ultra — which could not run TRELLIS.2 at all before this fork
(torch-MPS path was m3-only in practice) — now generates full-density
vertex-baked assets in ~3 min at 17GB. Install: clone
monster/trellis-2-mrp-mlx to ~/trellis2-mlx + scripts/setup_macos.sh
(PYTHON_BIN=uv 3.11) + gated weights rsynced from m3's HF cache
(no HF login needed on workers). Both Ultras now serve the fastest
local TRELLIS.2 in existence. TRELLIS.2 fleet: m3 primary (72s),
m1 second lane (182s), zero dollars per asset.

16
docs/FABLE_STARTUP_PACKET.md
View File

@ -500,3 +500,19 @@ Honest negatives (documented so nobody re-chases them):
Env knobs (all default-sane): TRELLIS2_MLX_SAMPLER=0 (revert sampler),
TRELLIS2_MLX_COMPILE=1, TRELLIS2_METAL_SPCONV=1.
M1 Ultra validation: in flight (26.5GB peak fits with 100GB headroom).
### Rung-3 addendum — M1 Ultra validated (2026-07-20)
| box | e2e wall | peak mem |
|---|---|---|
| m3ultra | 71.96 s | 26.5 GB |
| **m1ultra** | **181.5 s** | **17.2 GB** |
The M1 Ultra — which could not run TRELLIS.2 at all before this fork
(torch-MPS path was m3-only in practice) — now generates full-density
vertex-baked assets in ~3 min at 17GB. Install: clone
monster/trellis-2-mrp-mlx to ~/trellis2-mlx + scripts/setup_macos.sh
(PYTHON_BIN=uv 3.11) + gated weights rsynced from m3's HF cache
(no HF login needed on workers). Both Ultras now serve the fastest
local TRELLIS.2 in existence. TRELLIS.2 fleet: m3 primary (72s),
m1 second lane (182s), zero dollars per asset.