Prerequisites

• I have searched existing issues and reviewed documentation.

Problem Description

Current sllm store only shares parameter using GPU handle, it would be more beneficial if the pin memory pool can be shared to support offloading enabled applications.

Proposed Solution

• Add new memory pool using pinned and shared memory allocator
• Add interface to get CPU handle, i.e., shm_name

Alternatives Considered

No response

Additional Context

No response

Importance

Nice to have

Usage Statistics (Optional)

No response