Sheng Liu

Since version v0.2.5, it seems the stop parameter in openai api is directly set `conv.stop_str`, rather than from request. https://github.com/lm-sys/FastChat/blob/v0.2.5/fastchat/serve/api.py#L134 In version v0.2.3, it works when set in the request....

Hi djl developers, I'd like to combine the [image classification on spark demo](https://github.com/deepjavalibrary/djl-demo/blob/master/apache-spark/image-classification/src/main/scala/com/examples/ImageClassificationExample.scala) and [chatbot demo](https://github.com/deepjavalibrary/djl-demo/blob/master/huggingface/nlp/src/main/java/com/examples/Chatbot.java) to build llama.cpp on spark, following the design and conventions in djl spark extension....