This article establishes an RTHS framework based on Python and graphics processor unit （GPU） computation. Using a soil-structure interaction system as a testing model， the performance of the testing framework is verified by numerical simulation and experiment. The results show that using Python-GPU to speed the unconditionally stable algorithm allows a numerical sub‐structure with 24000 DOFs to be solved in a time step of 20 ms. Because the scale of GPU calculation is almost 7 times greater than that of CPU calculation in the same machine， the capability of RTHS is greatly extended.