Skip to content

[Option] Add option to set class Var id attribute to 0 by default#393

Merged
yaoyaoding merged 4 commits intohidet-org:mainfrom
destefy:var_id
Dec 15, 2023
Merged

[Option] Add option to set class Var id attribute to 0 by default#393
yaoyaoding merged 4 commits intohidet-org:mainfrom
destefy:var_id

Conversation

@destefy
Copy link
Copy Markdown
Contributor

@destefy destefy commented Dec 14, 2023

By default Var instances will have an id of 0.

This is to ensure that each entire FlowGraph is entirely deterministic given the same interpreter+input.

Copy link
Copy Markdown
Member

@yaoyaoding yaoyaoding left a comment

Choose a reason for hiding this comment

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

Thanks @destefy!
Left two minor suggestions.

@yaoyaoding
Copy link
Copy Markdown
Member

Thanks @destefy!

@yaoyaoding yaoyaoding merged commit e7f2efd into hidet-org:main Dec 15, 2023
@destefy destefy deleted the var_id branch December 19, 2023 14:28
vadiklyutiy pushed a commit that referenced this pull request Dec 19, 2024
…rm` during operator fusion pass (#437)

Closes #393 

I spent some time looking into the issue without much progress, but I
first found that the error message in the linked issue disappeared after
commenting out either the `resolve_variant_pass()` or
`fuse_operator_pass()`
[here](https://github.com/CentML/hidet/blob/bfbb4db6d7792ed3de3be4e9702e597b8fbbe373/python/hidet/graph/transforms/__init__.py#L55-L61).
Then, I found that simply adding the `EmbeddingBagOp` to the
`NOT_FUSIBLE` set resolves the error.

It is a workaround for now, but I am unaware of better solutions.
vadiklyutiy pushed a commit that referenced this pull request Dec 20, 2024
…rm` during operator fusion pass (#437)

Closes #393 

I spent some time looking into the issue without much progress, but I
first found that the error message in the linked issue disappeared after
commenting out either the `resolve_variant_pass()` or
`fuse_operator_pass()`
[here](https://github.com/CentML/hidet/blob/bfbb4db6d7792ed3de3be4e9702e597b8fbbe373/python/hidet/graph/transforms/__init__.py#L55-L61).
Then, I found that simply adding the `EmbeddingBagOp` to the
`NOT_FUSIBLE` set resolves the error.

It is a workaround for now, but I am unaware of better solutions.
vadiklyutiy pushed a commit that referenced this pull request Dec 26, 2024
…rm` during operator fusion pass (#437)

Closes #393 

I spent some time looking into the issue without much progress, but I
first found that the error message in the linked issue disappeared after
commenting out either the `resolve_variant_pass()` or
`fuse_operator_pass()`
[here](https://github.com/CentML/hidet/blob/bfbb4db6d7792ed3de3be4e9702e597b8fbbe373/python/hidet/graph/transforms/__init__.py#L55-L61).
Then, I found that simply adding the `EmbeddingBagOp` to the
`NOT_FUSIBLE` set resolves the error.

It is a workaround for now, but I am unaware of better solutions.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants