Function check_e4m3_activation_range 

pub fn check_e4m3_activation_range(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    input: DevicePtr,
    m: u32,
    k: u32,
    stream: u64,
) -> Result<()>

2026-09-29: When kernel casts its A operand to E4M3 with no scale, check the [m, k] BF16 input it reads (see check_e4m3_range). A no-op otherwise, and in release builds.