Add a dora-lmdeploy node

[haixuanTao]

LmDeploy showcase great performance on inference on Cuda and it could be great to wrap a node called dora-lmdeploy that could specify the model we want to use and handle the logic around receiving text and images.

It would probably be very similar to https://github.com/dora-rs/dora/blob/main/node-hub/dora-qwen2-5-vl except that we replace transformers with lmdeploy pipelines.

[7SOMAY]

Please assign this issue to me!

[Shar-jeel-Sajid]

@dora-bot assign me

[github-actions]

Hello @Shar-jeel-Sajid, this issue is now assigned to you!

[7SOMAY]

@dora-bot assign me

[github-actions]

Hello @7SOMAY, this issue is now assigned to you!