monster/corridorkey-mrp-mlx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: M-series fleet ablation (M3 Ultra / M1 Ultra / M4 Pro 24GB)

Browse Source 
Ran scripts/bench_optimizations.py unmodified across three machines + an
engine-level tiled×compile extension with ground-truth alpha scoring.
Headlines: sdpa = 4.5x regression on M1 at 2048 (bf16 innocent — isolated
per-toggle on both Ultras); stage_gc harmful on Ultra-class; tiled 768/64
+ compile = best 2048 config on both Ultras; 24GB Macs swap-bound at 2048
full-frame (tiled required).
This commit is contained in:
modelbeast 2026-07-16 22:48:06 +10:00
parent 4c660dff3c
commit a9f6b75ef2
1 changed files with 120 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

120
docs/2026-07-16-m-series-fleet-ablation-results.md Normal file
View File

@ -0,0 +1,120 @@
---
title: "M-series fleet ablation: M3 Ultra / M1 Ultra / M4 Pro"
date: 2026-07-16
device: "M3 Ultra 256GB · M1 Ultra 128GB (64-core GPU) · M4 Pro Mac mini 24GB"
script: scripts/bench_optimizations.py (unmodified) + engine-level tiled×compile extension
---
# M-series Fleet Ablation Benchmarks
Same methodology as the 2026-03-09 wave2 doc (`--sweep ablation --resolution 512 1024 2048`,
checkpoint weights, 3 warmup + 10 bench runs), executed on three machines spanning the
Apple Silicon range. Contributed from a 3-Mac render-farm setup; happy to run follow-ups.
## Headline findings
1. **`sdpa` is a ~4.5× regression on M1-class GPUs at 2048 — and free on M3.** Single-toggle
isolation at 2048 (median of 6, all-off baseline):
| toggle | M1 Ultra | M3 Ultra |
|---|---|---|
| all off | 4139 ms | 1743 ms |
| **bf16 only** | **4120 ms (neutral!)** | 1766 ms |
| **sdpa only** | **18592 ms (4.5× slower)** | 1763 ms |
| bf16+sdpa | 6388 ms | 1767 ms |
The suspected M1 danger (bf16 emulation — M1 lacks hardware bf16) is **innocent** on this
workload; `mx.fast.scaled_dot_product_attention` at 2048-scale sequence lengths is the
cliff. bf16 partially mitigates it (fp32 sdpa is the worst path). Suggestion: gate
`use_sdpa` by GPU generation rather than defaulting it on. (This may interest MLX
upstream too — it looks like a Metal kernel path issue on M1, not a model issue.)
2. **`stage_gc` is harmful on Ultra-class machines at every resolution** — 0.53× at 512,
0.64× at 1024, 0.66× at 2048 on M3 Ultra, for a 1–5 % peak-memory saving. Wave2 measured
a mild 0.79–0.99× on its reference hardware; on big-memory machines it's pure overhead.
Suggestion: document as a low-memory-only flag.
3. **Tiled + compile is the best 2048 config on both Ultras** — upstream `engine.py` forced
`compile=False` in tiled mode; tiles are fixed-shape, so fused compilation applies
(patched in this fork, output bit-identical, verified against ground-truth alpha):
| engine config (2048 input) | M3 Ultra | M1 Ultra | peak | alpha MAE* |
|---|---|---|---|---|
| full-frame 2048 | 2788 ms | 5373 ms | 27.9 GB | 0.00906 |
| tiled 512/64 | 2760 ms | 4576 ms | 2.2 GB | **0.00821** |
| tiled 512/64 + compile | 2478 ms | 4222 ms | 2.3 GB | **0.00821** |
| **tiled 768/64 + compile** | **1949 ms** | **3275 ms** | 2.4 GB | 0.00842 |
| tiled 1024/64 + compile | 3475 ms | 5864 ms | 3.7 GB | 0.00915 |
\*alpha MAE vs exact ground truth: synthetic 2048² green-screen plates (soft-alpha
subject + motion-blur stripes + defocus disk composited over chroma green), hint =
8× downscaled truth. Tiled beats full-frame on *accuracy* as well as memory — the model
runs at native tile scale over full-res input. Confirms wave2's tiled-768 pick and adds
~8–13 % from compiling the tile graph.
4. **24 GB Macs must tile at 2048.** On the M4 Pro mini (24 GB), every full-frame 2048
config lands at 20–24 s/run — the ~26 GB working set swaps; toggle choice becomes noise.
At ≤1024 the M4 is healthy (218 ms @512, 1149 ms @1024). Tiled 2048 runs in ~2.3 GB.
## Cross-machine baselines (all-off)
| res | M3 Ultra | M1 Ultra | M4 Pro 24GB | wave2 reference |
|---|---|---|---|---|
| 512 | 53.3 ms | 80.8 ms | 218.1 ms | 119.6 ms |
| 1024 | 247.0 ms | 350.6 ms | 1149.2 ms | 610.7 ms |
| 2048 | 1750.2 ms | 3527.3 ms | 23147 ms (swap) | 4984.7 ms |
## Full ablation tables
### M3 Ultra 256GB
| Config | 512 | 1024 | 2048 | peak @2048 |
|---|---|---|---|---|
| baseline | 53.3 | 247.0 | 1750.2 | 26689 MB |
| slim+sdpa+bf16+fused_decode+gpu_preprocess | 53.5 | 248.2 | 1790.1 | 27245 MB |
| slim+stage_gc+bf16+fused_decode+gpu_preprocess | 95.4 | 382.7 | 2644.3 | 26689 MB |
| slim+stage_gc+sdpa+fused_decode+gpu_preprocess | 96.3 | 385.9 | 2676.9 | 26661 MB |
| slim+stage_gc+sdpa+bf16+gpu_preprocess | 99.4 | 372.1 | 2618.6 | 26661 MB |
| slim+stage_gc+sdpa+bf16+fused_decode | 99.0 | 386.5 | 2688.0 | 26661 MB |
| stage_gc+sdpa+bf16+fused_decode+gpu_preprocess | 100.1 | 391.4 | 2628.2 | 26661 MB |
| slim+stage_gc+sdpa+bf16+fused_decode+gpu_preprocess | 101.0 | 390.9 | 2617.9 | 26661 MB |
### M1 Ultra 128GB
| Config | 512 | 1024 | 2048 | peak @2048 |
|---|---|---|---|---|
| baseline | 80.8 | 350.6 | 3527.3 | 26689 MB |
| slim+sdpa+bf16+fused_decode+gpu_preprocess | 79.1 | 353.3 | **33137.8** | 27245 MB |
| slim+stage_gc+bf16+fused_decode+gpu_preprocess | 189.5 | 705.5 | 4919.0 | 26689 MB |
| slim+stage_gc+sdpa+fused_decode+gpu_preprocess | 195.6 | 711.1 | 4939.2 | 26661 MB |
| slim+stage_gc+sdpa+bf16+gpu_preprocess | 198.2 | 681.6 | 4853.8 | 26661 MB |
| slim+stage_gc+sdpa+bf16+fused_decode | 197.7 | 714.1 | 4822.9 | 26661 MB |
| stage_gc+sdpa+bf16+fused_decode+gpu_preprocess | 194.2 | 733.2 | 6274.1 | 26661 MB |
| slim+stage_gc+sdpa+bf16+fused_decode+gpu_preprocess | 193.8 | 737.1 | 5128.2 | 26661 MB |
Note the 33.1 s outlier: the only 2048 config *without* `stage_gc` but *with* `sdpa` —
sdpa's slow path dominating once nothing throttles it (see headline 1 for the isolation).
The sdpa cliff appears only at 2048; 512/1024 are unaffected.
### M4 Pro Mac mini 24GB
| Config | 512 | 1024 | 2048 (swap-bound) |
|---|---|---|---|
| baseline | 218.1 | 1149.2 | 23147.1 |
| slim+sdpa+bf16+fused_decode+gpu_preprocess | 221.4 | 1139.0 | 20994.5 |
| slim+stage_gc+… (all stage_gc combos) | 266–273 | 1268–1292 | 20233–24253 |
At 2048 the ~26 GB working set exceeds 24 GB unified memory; all configs swap and
differences are not meaningful. ≤1024 full-frame or tiled-anything is the usable envelope.
## Recommended settings by hardware
| Hardware | 2048 recommendation |
|---|---|
| M3-class (Max/Ultra) | full-frame or tiled 768/64 + compile; every toggle optional; avoid `stage_gc` |
| M1/M2-class | **avoid `sdpa`**; tiled 768/64 + compile; avoid `stage_gc` |
| ≤24–32 GB any gen | **tiled required** (2.3 GB vs 26 GB); tiled 768/64 + compile |
*Environment: MLX (venv per `uv sync --extra mlx`), macOS 26.5, checkpoint v1.0.0. Quality
harness (ground-truth plates + scoring) available on request — it's ~150 lines and
reproduces the alpha-MAE column.*