GPU decode error

I run the code in docker container and its image is pytorch/pytorch:1.7.1-cuda11.0-cudnn8-devel.
I follow the example and build successfully, but something wrong happen
```python
from decord import VideoReader
from decord import cpu, gpu
video='/data/Celeb-DF-v2/YouTube-real/00000.mp4'
vr = VideoReader(video, ctx=gpu(0))
frames = vr.get_batch([1, 3, 5, 7, 9])
```
The error pops out like:
```python
CUDA error 3000 at line 341 in file /workspace/decord/src/video/nvcodec/cuda_threaded_decoder.cc: Traceback (most recent call last):
File "/workspace/decord/python/test.py", line 5, in
x = vr[1]
File "/workspace/decord/python/decord/video_reader.py", line 104, in __getitem__
self.seek_accurate(idx)
File "/workspace/decord/python/decord/video_reader.py", line 232, in seek_accurate
success = _CAPI_VideoReaderSeekAccurate(self._handle, pos)
File "/workspace/decord/python/decord/_ffi/_ctypes/function.py", line 174, in __call__
check_call(_LIB.DECORDFuncCall(
File "/workspace/decord/python/decord/_ffi/base.py", line 78, in check_call
raise DECORDError(err_str)
decord._ffi.base.DECORDError: [11:17:09] /workspace/decord/src/video/nvcodec/cuda_threaded_decoder.cc:270: Check failed: run_.load():
```
Env:ffmpeg 4.3.2,cuda 11.0,RTX 2080 Ti,Ubuntu 18.04