ffn_batch16_enabled

metrale_model_layers::layers::dense_ffn::batch16_decode

Function ffn_batch16_enabled 

Source 
pub fn ffn_batch16_enabled() -> bool
Expand description

2026-09-25: Whether METRALE_FFN_BATCH16 is exactly 1, which arms the tier; any other value, or none, leaves it off. Read once per process; each DenseFfnLayer copies it into batch16_enabled at construction, so the route cannot change between CUDA-graph replays.