epic: cortex.cpp benchmark + Backend Infra

[nguyenhoangthuan99]

Currently the example server for cortex.llamacpp and cortex.tensorrtllm can get the following resuls: With avg contex length 400:

• cortex.llamacpp: 850 token/s
• cortex.tensorrt-llm: 1450 token/s

We need to benchmark cortex-cpp server and make sure performance of cortex-cpp corresponding to example server