Dask xgboost partial dependence plots?

Hi, I am new to using dask and xgboost. In the research I am working on, it is necessary to examine fitted relationship between predictors and predictand, e.g., using partial dependence plot. Since my data set is too large to fit into memory, I have to use the distributed interface of xgboost. But the results do not seem to work with the sklearn interface for partial dependence plots. Could anyone help me with finding a solution? Thanks!