Version compatibility problem

[wyhfc123]

trafficstars

A new version of vllm is available, which supports inference using bnb quantization. The properties of the vllm SamplingParams class have changed in the latest vllm version, but the fastchat code does not appear to have been updated to accommodate the new version of vllm, resulting in a package version compatibility issue. Here is the error message for accessing the model: TypeError: Unexpected keyword argument 'use beam search'