Deep learning (DL) techniques are shown to be effective in many challenging tasks, and are hence widely-adopted in practice. However, previous work has shown that DL libraries, the basis of building and executing DL models, contain bugs and can cause severe consequences. Unfortunately, existing approaches still cannot comprehensively excise DL libraries. They utilize existing trained models and only detect bugs in model inference phase. In this work we propose Muffin to address these issues. To this end, Muffin applies a specifically-designed model fuzzing approach, which allows it to generate tremendous diverse DL models to explore the target library, instead of relying only on existing trained models. Muffin makes differential testing feasible in the model training phase by tailoring a set of metrics to measure the inconsistency between different DL libraries. In this way, Muffin can best excise the library code to detect more bugs. To evaluate the effectiveness of Muffin, we conduct experiments on three widely-used DL libraries. The results demonstrate that Muffin can detect 39 new bugs in the latest release versions of these libraries.