TensorRT  7.2.1.6
NVIDIA TensorRT
Looking for a C++ dev who knows TensorRT?
I'm looking for work. Hire me!
All Classes Namespaces Functions Variables Typedefs Enumerations Enumerator Friends Pages
polygraphy.backend.trt.loader.LoadPlugins Class Reference
Inheritance diagram for polygraphy.backend.trt.loader.LoadPlugins:
Collaboration diagram for polygraphy.backend.trt.loader.LoadPlugins:

Public Member Functions

def __init__ (self, obj=None, plugins=None)
 
def __call__ (self, *args, **kwargs)
 

Public Attributes

 obj
 
 plugins
 

Constructor & Destructor Documentation

◆ __init__()

def polygraphy.backend.trt.loader.LoadPlugins.__init__ (   self,
  obj = None,
  plugins = None 
)
A passthrough loader that loads plugins from the specified paths.
Passthrough here means that it can be used to wrap any other loader. The purpose of wrapping
another loader is that you can control the order of execution when lazily evaluating.

For immediate evaluation, call the loader. For example:
::

    from polygraphy.common import func
    func.invoke(LoadPlugins(plugins=["/path/to/my/plugin.so", "/path/to/my/other_plugin.so"]))

Args:
    obj (object):
    Any object to pass through this loader.
    If ``obj`` is callable, parameters to __call__ will be forwarded
    to ``obj`` when this loader is called.
    plugins (List[str]):
    A list of paths to plugin libraries to load before inference.

Member Function Documentation

◆ __call__()

def polygraphy.backend.trt.loader.LoadPlugins.__call__ (   self,
args,
**  kwargs 
)

Member Data Documentation

◆ obj

polygraphy.backend.trt.loader.LoadPlugins.obj

◆ plugins

polygraphy.backend.trt.loader.LoadPlugins.plugins

The documentation for this class was generated from the following file: