sigmoid_blend_device

Function sigmoid_blend_device 

Source
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)