UCT/ROCM: initial commit for device initiated ipc put (#11299)

Introduces device initiated IPC put operation for the ROCm component.

- Add device-side rocm_ipc.h with HIP __device__ put/atomic_add/get_ptr,
  including a strided int4/int2 vectorized copy at thread/warp/block levels.
- Add MD mem_elem_pack/rkey_ptr that map the remote IPC handle via a shared,
  lazily-initialized process-wide handle cache; iface/ep now expose a device ep.