Praveen Venkateswaran

Still seeing this issue as of Langchain 0.0.279 This is a problem, since using the `HuggingFacePipeline.from_model_id` approach enforces that the device value is always set (default is `-1`) This interferes...

@chrispan68 Do you mind sharing a code snippet of how you implement `subprocess` for the model serving and the client calls? I've tried using the flag that you added in...

Thank you so much!! A followup question -- What does `lmql_model_server_running()` do? Do you keep checking if `port 8080` can be connected to? I was trying to do that using...