• L
    Fix memory overwriting of tensors returned by executor (#19030) · 8f537354
    Leo Chen 提交于
    * fix memory overlapping of fetch var (return of executor.run), test=develop
    
    * fix wrong usage of ParallelExecutor in op_test, test=develop
    
    * remove useless parameter and simplify code
    
    * avoid tensor destruct untimely, test=develop
    
    * add testcase independent of OpTest, test=develop
    8f537354
op_test.py 26.0 KB