Function softplus_gate_mul_head_broadcast 

pub fn softplus_gate_mul_head_broadcast(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    input: DevicePtr,
    gate: DevicePtr,
    output: DevicePtr,
    nq: u32,
    hd: u32,
    num_tokens: u32,
    stream: u64,
) -> Result<()>

2026-09-25: Like sigmoid_gate_mul_head_broadcast with softplus in place of sigmoid (kernel softplus_gate_mul_head_broadcast).