This research focuses on a parallel machines scheduling problem considering lot streaming which is similar to the traditional hybrid flow shop scheduling (HFS). In a typical HFS with parallel machines problem, the allocation of machine resources for each order should be determined in advance. In addition, the size of each sublot is splited by parallel machines configuration. However, allocation of machine resources, sublot size and lot sequence are highly mutual influence. If allocation of machine resources has been determined, adjustment on production sequence is unable to reduce production makespan. Without splitting a given job into sublots, the production scheduling cannot have overlapping of successive operations in multi-stage parallel machines environment thereby contributing to the best production scheduling. Therefore, this research motivated from a solar cell industry is going to explore these issues. The multi-stage and parallel-machines scheduling problem in the solar cell industry simultaneously considers the optimal sublot size, sublot sequence, parallel machines sublot scheduling and machine configurations through dynamically allocating all sublot to parallel machines. We formulate this problem as a mixed integer linear programming (MILP) model considering the practical characteristics including parallel machines, dedicated machines, sequence-independent setup time, and sequence-dependent setup time. A hybrid-coded particle swarm optimization (HCPSO) is developed to find a near-optimal solution. At the end of this study, the result of this research will compare with the optimization method of mixed integer linear programming and case study.