NvidiaMpsAllocation
The GPU memory and compute limits for a container that shares a GPU by using NVIDIA Multi-Process Service (MPS). Amazon ECS assigns the container a single GPU that has enough memory available. Other containers that use MPS can share the same GPU.
Contents
- 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_LIMITenvironment 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 usesnvidiaMps, Amazon ECS assigns them the same GPU, which must have enough memory available for all of them.Type: Integer
Valid Range: Minimum value of 1.
Required: Yes
- maxComputePercent
-
The maximum percentage of the GPU's compute capacity that the container can use. Amazon ECS sets the
CUDA_MPS_ACTIVE_THREAD_PERCENTAGEenvironment 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.Type: Integer
Valid Range: Minimum value of 1. Maximum value of 100.
Required: No
See Also
For more information about using this API in one of the language-specific Amazon SDKs, see the following: