Skip to main content

select_precision

qualia_core_db::platform::hetero_dispatch

Function select_precision 

Source 
pub fn select_precision(
    param_count: u64,
    budget: &PowerThermalBudget,
) -> Precision
Expand description

Pick the precision tuned to the host’s thermodynamic / power / memory constraints: choose the coarsest precision that still fits param_count weights in the VRAM budget, and — when power or thermal headroom is tight — never run the heavy precisions (f32/f16 draw more power and generate more heat). Returns Q4 if even q4 overflows VRAM (the caller must then tile or offload).