corridorkey-mrp-mlx/docs
modelbeast 1cb02ec4fa docs: 8 machines — tiled keys 2048 on the 2020 M1 mini 8GB, same accuracy
Completes every Apple Silicon GPU generation ever shipped (M1 2020 -> M5).
Headline: tiled 768/64+compile keys a full 2048 frame in ~2.2GB on EVERY
machine with IDENTICAL alpha (MAE 0.00849) — M3 Ultra 1949ms ... M1 mini 8GB
14269ms. Full-frame needs 26GB and is unreachable for most Macs ever sold, so
tiled should arguably be the default, not the fallback. The README's 'might
even work on your old MacBook Pro' undersells it.
Also: real CorridorKey ablation on M1 Max (stage_gc harmful at 32GB too:
0.81x @512), and the OG 8-core M1 mini confirms the hdim-56 fallback (1.00x
x3, padding 1.9x) — now 8/8 machines.
2026-07-17 15:03:08 +10:00
..
benchmarks docs: wave2 ablation benchmarks + optimization plan + brainstorm 2026-03-09 19:32:04 -02:30
brainstorms docs: wave2 ablation benchmarks + optimization plan + brainstorm 2026-03-09 19:32:04 -02:30
plans docs: wave2 ablation benchmarks + optimization plan + brainstorm 2026-03-09 19:32:04 -02:30
2026-07-16-m-series-fleet-ablation-results.md docs: 8 machines — tiled keys 2048 on the 2020 M1 mini 8GB, same accuracy 2026-07-17 15:03:08 +10:00
MLX Vision Transformer Optimization Techniques.md docs: wave2 ablation benchmarks + optimization plan + brainstorm 2026-03-09 19:32:04 -02:30