Move `TopKKernel` behind `GpuKernelRegistry`.

[copybara-service[bot]]

Move TopKKernel behind GpuKernelRegistry.

• Moves TopK logic into backends/gpu/runtime since it's a runtime component.
• Defines trait for the TopK kernel in stream_executor/gpu/
• Moves the implementations of this kernel into stream_executor/{cuda|rocm} and registers them with the registry for each xla::primitive_util::Type.
• Makes TopK retrieve the kernel by using the kernel registry.
• Add the kernel implementations as dependencies to the all_runtime targets for CUDA and ROCm.