vad .onnx transform to tensorRT erro

[huxiaomin369]

I use the command to transform .onnx model to .engine model

trtexec --onnx=scratch/vadv1.pts_bbox_head.forward/sim_vadv1.pts_bbox_head.forward.onnx \
        --plugins=../plugins/build/libplugins.so \
        --profilingVerbosity=detailed --dumpProfile \
        --separateProfileRun --useSpinWait --useManagedMemory \
        --saveEngine=vadv1.pts_bbox_head.forward/vadv1.pts_bbox_head.forward.engine

but it comes to error

[10/14/2025-07:02:42] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
[10/14/2025-07:03:02] [I] [TRT] Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.
[10/14/2025-07:03:33] [W] [TRT] Skipping tactic 0 due to insuficient memory on requested size of 121600000 detected for tactic 0.
[10/14/2025-07:03:33] [E] Error[10]: [optimizer.cpp::computeCosts::2011] Error Code 10: Internal Error (Could not find any implementation for node {ForeignNode[onnx::Gather_626...Cast_1162]}.)
[10/14/2025-07:03:33] [E] Error[2]: [builder.cpp::buildSerializedNetwork::609] Error Code 2: Internal Error (Assertion enginePtr != nullptr failed. )
[10/14/2025-07:03:33] [E] Engine could not be created from network
[10/14/2025-07:03:33] [E] Building engine failed
[10/14/2025-07:03:33] [E] Failed to create engine from model.
[10/14/2025-07:03:33] [E] Engine set up failed
&&&& FAILED TensorRT.trtexec [TensorRT v8204] # trtexec --onnx=scratch/vadv1.pts_bbox_head.forward/sim_vadv1.pts_bbox_head.forward.onnx --plugins=../plugins/build/libplugins.so --profilingVerbosity=detailed --dumpProfile --separateProfileRun --useSpinWait --useManagedMemory --saveEngine=vadv1.pts_bbox_head.forward/vadv1.pts_bbox_head.forward.engine

How can i fix it?