The GRASPG program package is an extension to GRASP2018 (Froese Fischer et al. (2019) [1]) based on configuration state function generators (CSFGs). The generators keep spin-angular integrations at a minimum and reduce substantially the execution time and the memory requirement for large-scale multiconfiguration Dirac-Hartree-Fock (MCDHF) and relativistic configuration interaction (CI) atomic structure calculations. The package includes the improvements reported in Li (2023) [8] in terms of redesigned and efficient constructions of direct and exchange potentials and Lagrange multipliers. In addition, further parallelization of the diagonalization procedure has been implemented. Tools have been developed for predicting configuration state functions (CSFs) that are unimportant and can be discarded for large MCDHF or CI calculations based on results from smaller calculations, thus providing efficient methods for a priori condensation. The package provides a seamless interoperability with GRASP2018. From extensive test runs and benchmarking, we have demonstrated reductions in the execution time and disk file sizes with factors of 37 and 98, respectively, for MCDHF calculations based on large orbital sets compared to corresponding GRASP2018 calculations. For CI calculations, reductions of the execution time with factors over 200 have been attained. With a sensible use of the new possibilities for a priori condensation, CI calculations with nominally hundreds of millions of CSFs can be handled. PROGRAM SUMMARY Program Title: GRASPG CPC Library link to program files: https://doi.org/10.17632/7b5kbhy3v9.1 Licensing provisions: MIT License Programming language: Fortran 95 Nature of problem: Prediction of atomic energy levels using a multiconfiguration Dirac–Hartree–Fock approach. Solution method: The computational method is the same as in GRASP2018 [1] except that configuration state function generators (CSFGs) have been introduced, a concept that substantially reduces the execution times and memory requirements for large-scale calculations [2]. The method also relies on redesigned and more efficient constructions of direct and exchange potentials and Lagrange multipliers, along with additional parallelization of the diagonalization procedure as detailed in [3]. Additional comments including restrictions and unusual features: 1. provides a seamless interoperability with GRASP2018, 2. options to limit the Breit interaction, 3. includes tools for predicting CSFs that are unimportant and can be discarded for large MCDHF or CI calculations based on the results from smaller calculations. References [1] C. Froese Fischer, G. Gaigalas, P. Jönsson, and J. Bieroń, Comput. Phys. Commun. 237 (2019) 184-187. [2] Y. Li, K. Wang, R. Si et al. Comput. Phys. Commun. 283 (2023) 108562. [3] Y. Li, J. Li, C. Song et al. Atoms 11 (2023) 12.