Change custom_skip_targets meaning for constant_prop_pass

pytorch / executorch

On-device AI across mobile, embedded and edge for PyTorch

https://pytorch.org/executorch/

Other

1.31k stars 206 forks source link

Change custom_skip_targets meaning for constant_prop_pass #3491

Closed dulinriley closed 1 week ago

dulinriley commented 2 weeks ago

Summary: Some users of constant_prop_pass want to fold across calls to full, because representing a tensor as a program constant is a requirement for some backends. This came up when writing some tests using torch.ones as a weight tensor, which is represented as aten.full in Edge Dialect.

When the user specifies a custom skip set, do not add the default aten.full function, in case the user doesn't want it.

Differential Revision: D56894215

pytorch-bot[bot] commented 2 weeks ago

:link: Helpful Links

:test_tube: See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/3491

:page_facing_up: Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

:white_check_mark: No Failures

As of commit fe6193e15de3d302cceaa73b0a97c1840871a909 with merge base c83af25b76254e96ad0e67ddb0593ad8d039dc66 (): :green_heart: Looks good so far! There are no failures yet. :green_heart: