IRuntimeConfig

tensorrt.ExecutionContextAllocationStrategy

Different memory allocation behaviors for IExecutionContext.

Members:

STATIC : Default static allocation with the maximum size across all profiles.

ON_PROFILE_CHANGE : Reallocate for a profile when it’s selected.

USER_MANAGED : The user supplies custom allocation to the execution context.

class tensorrt.IRuntimeConfig

A runtime configuration for an ICudaEngine .

__init__(*args, **kwargs)

get_execution_context_allocation_strategy(self: tensorrt.tensorrt.IRuntimeConfig) → tensorrt.tensorrt.ExecutionContextAllocationStrategy

Get the execution context allocation strategy.

Returns:

The execution context allocation strategy.

set_execution_context_allocation_strategy(self: tensorrt.tensorrt.IRuntimeConfig, strategy: tensorrt.tensorrt.ExecutionContextAllocationStrategy = <ExecutionContextAllocationStrategy.STATIC: 0>) → None

Set the execution context allocation strategy.

Parameters:

strategy – The execution context allocation strategy.