Skip to content

fix failures- cpu offloading casues device mismatch L2_dynamo_compile…#4089

Draft
apbose wants to merge 3 commits intomainfrom
abose/CI_error_fix
Draft

fix failures- cpu offloading casues device mismatch L2_dynamo_compile…#4089
apbose wants to merge 3 commits intomainfrom
abose/CI_error_fix

Conversation

@apbose
Copy link
Collaborator

@apbose apbose commented Feb 20, 2026

No description provided.

@meta-cla meta-cla bot added the cla signed label Feb 20, 2026
@github-actions github-actions bot added component: tests Issues re: Tests component: core Issues re: The core compiler component: api [Python] Issues re: Python API component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths labels Feb 20, 2026
@github-actions github-actions bot requested a review from zewenli98 February 20, 2026 21:27
@apbose apbose marked this pull request as draft February 20, 2026 21:28
f"Conversion of module {gm} not currently fully supported or convertible!",
exc_info=True,
)
raise
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If we are throwing exceptions, provide an actual error type and explanation

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The bare raise should be able to catch the same exception object or the UnsupportedOperatorException. Do we need another exception message. That would be code repeat. But can add.

exp_program,
inputs=[input_tensor],
enabled_precisions={torch.float8_e4m3fn},
use_explicit_typing=False,
Copy link
Collaborator

@narendasan narendasan Feb 22, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is deprecated, this test should be ported to explicit typing

@apbose apbose force-pushed the abose/CI_error_fix branch 2 times, most recently from 775cd03 to e33ca90 Compare February 23, 2026 19:41
@apbose
Copy link
Collaborator Author

apbose commented Feb 24, 2026

@narendasan had discussion with @zewenli98. Should we remove this https://github.com/pytorch/TensorRT/blob/main/py/torch_tensorrt/dynamo/_compiler.py#L641-648 from the code, since explicit typing means that we should not provide precision now.
As for porting the test to explicit typing, that means is it meant that we should remove the enabled_precisions={torch.float8_e4m3fn} from test?

… tests, set explicit typing false for precisions test L2_torch_tensorrt_py_tests, and add raise exceptions for error logging
@apbose apbose force-pushed the abose/CI_error_fix branch from 794f9d9 to e06de0f Compare February 24, 2026 23:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

cla signed component: api [Python] Issues re: Python API component: core Issues re: The core compiler component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths component: tests Issues re: Tests

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants