[TensorRT] IRuntime::deserializeCudaEngine: Error Code 6: API Usage Error (The engine plan file is generated on an incompatible device, expecting compute 8.9 got compute 8.6, please rebuild.) [TensorRT error] failed to deserialize engine
Author: bruceborgiaCreated May 7, 2026Updated May 11, 2026
[TensorRT] IRuntime::deserializeCudaEngine: Error Code 6: API Usage Error (The engine plan file is generated on an incompatible device, expecting compute 8.9 got compute 8.6, please rebuild.) [TensorRT error] failed to deserialize engine [ERR: InferenceWrapperTensorRT][44] Failed to load TensorRT model NN Initialize fail
====================================== GPU:4090 CUDA:12.8 TENSORRT:10.8
加载Megatron_TRT时报错,这个怎么解决啊
Source: deepinsight/insightface