This PR implements cpu offload connector to enable NPU kv cache offload to host DRAM. - vLLM version: v0.10.2 - vLLM main: https://github.com/vllm-project/vllm/commit/5aeb9254521023f97aca292b3478aa7ff485ffb2 Signed-off-by: lidenghui <lidenghui1110@gmail.com> Signed-off-by: AlvisGong <gwly0401@163.com> Signed-off-by: CalvinXKY <kyxiezju@163.com> Co-authored-by: AlvisGong <gwly0401@163.com>