[WIP] Support InternLM on 3rd-party inference toolboxes

[wangruohui]

This issue is to track progress on 3rd party toolboxes which is related to InternLM.

VLLM

https://github.com/wangruohui/vllm/tree/internlm

• Inference with single GPU
  • There seems some bug, not sure from my implementation or from upstream
• Tensor parallel

DeepSpeed

InternLM-7B is supported in Deepspeed inference and merged to main branch: deepspeedai/DeepSpeed#4137

• Single GPU with kernel infection policy
• Tensor parallel

Meta tensor for faster model loading: watching deepspeedai/DeepSpeed#3608