Skip to content

Expand cuda.core.system to cover NVML functionalities #1211

@leofang

Description

@leofang

Tentative design considerations/constraints:

  1. Must not run cuInit(0) or initialize CUDA if all users need is querying via NVML
  2. Cover nvmlDeviceGetCpuAffinity, nvmlDeviceGetMemoryInfo, nvmlDeviceGetCount, ...

Metadata

Metadata

Assignees

Labels

P0High priority - Must do!blockedThis task is currently blocked by other taskscuda.coreEverything related to the cuda.core modulefeatureNew feature or request

Type

No type

Projects

No projects

Relationships

None yet

Development

No branches or pull requests

Issue actions