Skip to content

Prevent OOM-based app crashes #726

@chmjkb

Description

@chmjkb

Handle out-of-memory scenarios gracefully instead of crashing the app when ExecuTorch runtime fails to allocate memory for model operations.

Current State

  • App crashes when loading large models on memory-constrained devices
  • ExecuTorch runtime throws unrecoverable errors during memory allocation
  • No way to check available memory before loading a model
  • Users have no warning before crash occurs

Goals

  • Catch memory allocation failures before they crash the app
  • Provide memory estimation API so users can check before loading

Metadata

Metadata

Assignees

Labels

CoreexecutorchIssues and tasks related specifically to ExecuTorch

Type

Projects

No projects

Relationships

None yet

Development

No branches or pull requests

Issue actions