nvfp4_grouped_decode_shape_ok

metrale_model_layers::layers::moe

Function nvfp4_grouped_decode_shape_ok 

Source 
pub fn nvfp4_grouped_decode_shape_ok(
    m: usize,
    max_rows: usize,
    hidden: usize,
    inter: usize,
    shared_inter: usize,
) -> bool
Expand description

2026-09-27: Shape admission without a GPU: m in 1..=max_rows (2026-10-02: the selected expert kernels’ widest, NVFP4_GROUPED_DECODE_MAX_ROWS or NVFP4_GROUPED_DECODE_TC_MAX_ROWS), hidden % 32 == 0 (gate+up reads 32-element chunks) and inter % 16 == 0 (down reads 16-element blocks), and a shared expert as wide as a routed one (the shared SiLU product shares the routed layout).