MCPcopy Create free account
hub / github.com/NVIDIA/TensorRT / do_inference_v2

Function do_inference_v2

samples/python/common.py:260–263  ·  view source on GitHub ↗
(context, bindings, inputs, outputs, stream)

Source from the content-addressed store, hash-verified

258# This function is generalized for multiple inputs/outputs for full dimension networks.
259# inputs and outputs are expected to be lists of HostDeviceMem objects.
260def do_inference_v2(context, bindings, inputs, outputs, stream):
261 def execute_async():
262 context.execute_async_v2(bindings=bindings, stream_handle=stream)
263 return _do_inference_base(inputs, outputs, stream, execute_async)

Callers

nothing calls this directly

Calls 1

_do_inference_baseFunction · 0.85

Tested by

no test coverage detected