Interface NvidiaMpsAllocation.Builder

All Superinterfaces:
Buildable, CopyableBuilder<NvidiaMpsAllocation.Builder,NvidiaMpsAllocation>, SdkBuilder<NvidiaMpsAllocation.Builder,NvidiaMpsAllocation>, SdkPojo
Enclosing class:
NvidiaMpsAllocation
@Mutable @NotThreadSafe public static interface NvidiaMpsAllocation.Builder extends SdkPojo, CopyableBuilder<NvidiaMpsAllocation.Builder,NvidiaMpsAllocation>

  • Method Details

    • memory

      NvidiaMpsAllocation.Builder memory(Integer memory)

      The amount of GPU memory, in MiB, to allocate to the container. Amazon ECS assigns the container a GPU that has at least the specified amount of memory available, and sets the CUDA_MPS_PINNED_DEVICE_MEM_LIMIT environment variable in the container to limit its memory to this amount. The memory must be available on a single GPU. If more than one container in a task uses nvidiaMps, Amazon ECS assigns them the same GPU, which must have enough memory available for all of them.

      Parameters:
      memory - The amount of GPU memory, in MiB, to allocate to the container. Amazon ECS assigns the container a GPU that has at least the specified amount of memory available, and sets the CUDA_MPS_PINNED_DEVICE_MEM_LIMIT environment variable in the container to limit its memory to this amount. The memory must be available on a single GPU. If more than one container in a task uses nvidiaMps, Amazon ECS assigns them the same GPU, which must have enough memory available for all of them.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • maxComputePercent

      NvidiaMpsAllocation.Builder maxComputePercent(Integer maxComputePercent)

      The maximum percentage of the GPU's compute capacity that the container can use. Amazon ECS sets the CUDA_MPS_ACTIVE_THREAD_PERCENTAGE environment variable in the container to this value. This value is a limit, not a reservation.

      If you don't specify this parameter, Amazon ECS doesn't set CUDA_MPS_ACTIVE_THREAD_PERCENTAGE, and the active thread percentage of the MPS server on the container instance applies. By default, this is 100 percent.

      Parameters:
      maxComputePercent - The maximum percentage of the GPU's compute capacity that the container can use. Amazon ECS sets the CUDA_MPS_ACTIVE_THREAD_PERCENTAGE environment variable in the container to this value. This value is a limit, not a reservation.

      If you don't specify this parameter, Amazon ECS doesn't set CUDA_MPS_ACTIVE_THREAD_PERCENTAGE, and the active thread percentage of the MPS server on the container instance applies. By default, this is 100 percent.

      Returns:
      Returns a reference to this object so that method calls can be chained together.