2 Commits

Author	SHA1	Message	Date
cmoyates	e91089a804	docs: wave2 ablation benchmarks + optimization plan + brainstorm ... Ablation sweep across 512/1024/2048 resolutions with 8 configs. Tiled 768/64 = 1.5x faster + 11.4x less memory vs full-frame at 2048. stage_gc net negative at small res, breaks even at 2048. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-03-09 19:32:04 -02:30
cmoyates	830e88f050	docs: add brainstorm + plan for MLX memory optimizations ... bf16 mixed precision, batched decoder upsample, deterministic GC pipeline. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-03-08 21:12:59 -02:30