Skip to content

refactor: remove redundant tensor concatenation and slicing in forward pass - #491

Merged
lmxyy merged 1 commit into
nunchux-ai:mainfrom
Bluear7878:useless_code
Jul 27, 2025
Merged

lmxyy merged 1 commit into
nunchux-ai:mainfrom
Bluear7878:useless_code

Conversation

@Bluear7878

Copy link
Copy Markdown
Contributor

This PR removes two redundant lines of code from the model's forward pass.

These operations are unnecessary as they have no impact on the final output.

Removing them simplifies the logic and improves code readability.

@Bluear7878
Bluear7878 requested a review from ita9naiwa June 26, 2025 02:48
@lmxyy
lmxyy changed the base branch from dev to main July 14, 2025 17:39
@lmxyy lmxyy changed the title Refactor: Remove redundant tensor concatenation and slicing in forward pass refactor: remove redundant tensor concatenation and slicing in forward pass Jul 26, 2025
@lmxyy lmxyy closed this Jul 26, 2025
@lmxyy lmxyy reopened this Jul 26, 2025
@lmxyy lmxyy closed this Jul 27, 2025
@lmxyy lmxyy reopened this Jul 27, 2025
@lmxyy lmxyy closed this Jul 27, 2025
@lmxyy lmxyy reopened this Jul 27, 2025

@lmxyy lmxyy left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

passing all tests. approved

@lmxyy
lmxyy merged commit 577bd8e into nunchux-ai:main Jul 27, 2025
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