The number of default auxstream

In this trt document, I could find the discription about the way of set number of aux stream.

Additionally, according to the description of setMaxAuxStreams, I found trt automatically set the optimal number of aux streams if I don’t set the number of aux streams.

However, I built the engine without setting the number of aux streams and trying to getNbAuxStreams, the result of getNbAuxStreams().

Can I get the default number of aux streams?

    //!
    //! \brief Set the maximum number of auxiliary streams that TRT is allowed to use.
    //!
    //! If the network contains operators that can run in parallel, TRT can execute them using auxiliary streams
    //! in addition to the one provided to the IExecutionContext::enqueueV3() call.
    //!
    //! The default maximum number of auxiliary streams is determined by the heuristics in TensorRT on whether enabling
    //! multi-stream would improve the performance. This behavior can be overridden by calling this API to set the
    //! maximum number of auxiliary streams explicitly. Set this to 0 to enforce single-stream inference.
    //!
    //! The resulting engine may use fewer auxiliary streams than the maximum if the network does not contain enough
    //! parallelism or if TensorRT determines that using more auxiliary streams does not help improve the performance.
    //!
    //! \note Allowing more auxiliary streams does not always give better performance since there will be
    //! synchronizations overhead between streams. Using CUDA graphs at runtime can help reduce the overhead caused by
    //! cross-stream synchronizations.
    //!
    //! \note Using more auxiliary leads to more memory usage at runtime since some activation memory blocks will not
    //! be able to be reused.
    //!
    //! \param nbStreams The maximum number of auxiliary streams that TRT is allowed to use.
    //!
    //! \see getMaxAuxStreams(), ICudaEngine::getNbAuxStreams(), IExecutionContext::setAuxStreams()
    //!
    void setMaxAuxStreams(int32_t nbStreams) noexcept
    {
        mImpl->setMaxAuxStreams(nbStreams);
    }

Hi @yu.saito4 ,
The maximum number of auxiliary streams that TRT is allowed to use. If the network contains operators that can run in parallel, TRT can execute them using auxiliary streams in addition to the one provided to the IExecutionContext::enqueueV3() call. The default maximum number of auxiliary streams is determined by the heuristics in TensorRT on whether enabling multi-stream would improve the performance. This behavior can be overridden by calling this API to set the maximum number of auxiliary streams explicitly. Set this to 0 to enforce single-stream inference. The resulting engine may use fewer auxiliary streams than the maximum if the network does not contain enough parallelism or if TensorRT determines that using more auxiliary streams does not help improve the performance. Allowing more auxiliary streams does not always give better performance since there will be synchronizations overhead between streams. Using CUDA graphs at runtime can help reduce the overhead caused by cross-stream synchronizations. Using more auxiliary leads to more memory usage at runtime since some activation memory blocks will not be able to be reused.