run multiple models at one time on xavier

[jeansely]

Hi,
how can i take two model at same time on nvidia jetson xavier. with last update i have error.
[cuda.memcpy_htod_async(inp.device, inp.host, stream) for inp in inputs]
pycuda._driver.LogicError: cuMemcpyHtoDAsync failed: invalid argument
CException ignored in: <module 'threading' from '/usr/lib/python3.6/threading.py'>
Traceback (most recent call last):
File "/usr/lib/python3.6/threading.py", line 1294, in _shutdown
t.join()
File "/usr/lib/python3.6/threading.py", line 1056, in join
self._wait_for_tstate_lock()
File "/usr/lib/python3.6/threading.py", line 1072, in _wait_for_tstate_lock
elif lock.acquire(block, timeout):
KeyboardInterrupt
FATAL: exception not rethrown
Aborted (core dumped)

[ryanolson]

Jetson is outside the scope of this project. However, you can use the examples in this project to use TensorRT efficiently on Jetson. See Issue #35.

However, your example code above looks to be some issues with using pycuda.