CUDA cask failure when generating tensorrt models by tensorRT_optimization tool

I want to generate SSD model by tensorRT_optimization offered by driveworks 2.0. And I have finished the normalize layer and priorbox layer plugin class and compiled to libs without errors. But when I use the tensorRT_optimization tool use the following commond:
./tensorRT_optimization --modelType=caffe --outputBlobs=mbox_conf_flatten,mbox_priorbox,mbox_loc --prototxt=deploy.prototxt --caffemodel=VGG_VOC0712_SSD_300x300_iter_120000.caffemodel --pluginConfig=plugin.json

It failed. I have no way to localize the error since the tool have no source code. Here are the errors:

normalize_dwDNNPlugin_enqueue start
normalize_dwDNNPlugin_enqueue end
CUDA cask failure at execution for trt_maxwell_scudnn_128x64_relu_medium_nn_v1.
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
Iteration 1: 0 ms.
CUDA cask failure at execution for trt_maxwell_scudnn_128x64_relu_medium_nn_v1.
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
Iteration 2: 0 ms.
CUDA cask failure at execution for trt_maxwell_scudnn_128x64_relu_medium_nn_v1.
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
Iteration 3: 0 ms.
CUDA cask failure at execution for trt_maxwell_scudnn_128x64_relu_medium_nn_v1.
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
Iteration 4: 0 ms.
CUDA cask failure at execution for trt_maxwell_scudnn_128x64_relu_medium_nn_v1.
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
Iteration 5: 0 ms.
CUDA cask failure at execution for trt_maxwell_scudnn_128x64_relu_medium_nn_v1.
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
Iteration 6: 0 ms.
CUDA cask failure at execution for trt_maxwell_scudnn_128x64_relu_medium_nn_v1.
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
Iteration 7: 0 ms.
CUDA cask failure at execution for trt_maxwell_scudnn_128x64_relu_medium_nn_v1.
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
Iteration 8: 0 ms.
CUDA cask failure at execution for trt_maxwell_scudnn_128x64_relu_medium_nn_v1.
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 77
Iteration 9: 0 ms.
Average over 10 runs is 0 ms.
runtime.cpp (30) - Cuda Error in free: 77
terminate called after throwing an instance of ‘nvinfer1::CudaError’
what(): std::exception
Aborted (core dumped)

Dear huchenyang,
Can you check GPU details using CUDA deviceQuery samplr. Please confirm if you have > PAscal based GPU on host. If so, could you please check the issue on latest release(DRIVE SW 10).

Well, it outputs as follows:

Detected 1 CUDA Capable device(s)

Device 0: “GeForce GTX 1080 with Max-Q Design”
CUDA Driver Version / Runtime Version 10.1 / 10.0
CUDA Capability Major/Minor version number: 6.1
Total amount of global memory: 8114 MBytes (8508604416 bytes)
(20) Multiprocessors, (128) CUDA Cores/MP: 2560 CUDA Cores
GPU Max Clock rate: 1468 MHz (1.47 GHz)
Memory Clock rate: 5005 Mhz
Memory Bus Width: 256-bit
L2 Cache Size: 2097152 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 2 copy engine(s)
Run time limit on kernels: Yes
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
Device supports Unified Addressing (UVA): Yes
Device supports Compute Preemption: Yes
Supports Cooperative Kernel Launch: Yes
Supports MultiDevice Co-op Kernel Launch: Yes
Device PCI Domain ID / Bus ID / location ID: 0 / 1 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 10.1, CUDA Runtime Version = 10.0, NumDevs = 1
Result = PASS

Dear huchenyang,
It seems you have PASCAL based card. Do you see any issue with running drivenet sample?
Please share ldd tensorRT_optimization output to identify linked libs path.