TensorRT 10.0.1
IGpuAllocator Class Reference

Application-implemented class for controlling allocation on the GPU. More...

#include <NvInferRuntimeBase.h>

Detailed Description

Application-implemented class for controlling allocation on the GPU.

Warning
The lifetime of an IGpuAllocator object must exceed that of all objects that use it.

This class is intended as a base class for allocators that implement synchronous allocation. If you want the benefits of asynchronous allocation, you can do either of:

  • Derive your class from IGpuAllocator and override all four of its virtual methods for allocation/deallocation, including the two deprecated methods.
  • Derive your class from IGpuAsyncAllocator and override its two pure virtual methods for allocation/deallocation.

The latter style is preferred because it does not tie code to deprecated methods.

See also
IGpuAsyncAllocator.

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

  Copyright © 2024 NVIDIA Corporation
  Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact