Skip to content

Use SafeCast for float-to-integer conversions in CAST kernel - #3660

Open
veblush wants to merge 2 commits into
tensorflow:mainfrom
veblush:cast-fix
Open

Use SafeCast for float-to-integer conversions in CAST kernel#3660
veblush wants to merge 2 commits into
tensorflow:mainfrom
veblush:cast-fix

Conversation

@veblush

@veblush veblush commented Aug 13, 2026

Copy link
Copy Markdown
Collaborator

To align TFLM's CAST kernel with LiteRT, which already uses SafeCast for floating-point to integral conversions.

BUG=n/a

@veblush veblush added the ci:full Triggers the comprehensive cross-platform test suite. label Aug 13, 2026
@veblush
veblush requested a review from suleshahid August 13, 2026 01:24
@veblush
veblush marked this pull request as ready for review August 13, 2026 02:16
@veblush
veblush requested a review from a team as a code owner August 13, 2026 02:16
Comment thread tensorflow/lite/micro/kernels/cast_test.cc Outdated

@ddavis-2015 ddavis-2015 left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

looks good to me

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ci:full Triggers the comprehensive cross-platform test suite.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants