Route work to the Neural Engine.

Experimental execution paths that move selected mlx-go work (linear operations, draft models, decode stages) onto the Apple Neural Engine, with CPU and GPU fallback preserved.

Experiment. Intentionally narrow and not API-stable, in the repo's own words. Model assessment and routing helpers build everywhere; the block runtimes and IOSurface data plane are Darwin-only and require private-ANE build tags.

What it does

This experiment intercepts recognized mlx-go subgraphs and sends matching operations to the Neural Engine. It does not yet lower arbitrary graphs. Results from mlx-go-lm draft-model and decode experiments are reported as implementation findings, not rules about every ANE workload; gputrace measures the GPU side of the comparison.