pub fn sigmoid_blend_device(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
output: DevicePtr,
src: DevicePtr,
gate_ptr: DevicePtr,
num_elements: u32,
stream: u64,
) -> Result<()>Expand description
Sigmoid-gated blend reading gate scalar from device memory.
output[i] += sigmoid(bf16_to_f32(*gate_ptr)) * src[i]
Kernel: bf16_sigmoid_blend_device(output, src, gate_ptr, n)
Grid: (ceil(n/256), 1, 1) Block: (256, 1, 1)