Skip to content

Fix for issue #22974. Cast intermediate results to float before adding.#22994

Open
scutler-nv wants to merge 1 commit into
ggml-org:masterfrom
scutler-nv:scutler/issue_22974_fix
Open

Fix for issue #22974. Cast intermediate results to float before adding.#22994
scutler-nv wants to merge 1 commit into
ggml-org:masterfrom
scutler-nv:scutler/issue_22974_fix

Conversation

@scutler-nv
Copy link
Copy Markdown
Contributor

Overview

Fix for issue 22974. Cast intermediate results to float before adding and casting the result to the destination type. Avoids half+half operator ambiguity.

Requirements

None. Claude was used to develop the change.

…re adding and casting the result to the destination type. Avoids half+half operator ambiguity.
@scutler-nv scutler-nv requested a review from a team as a code owner May 13, 2026 00:17
@github-actions github-actions Bot added Nvidia GPU Issues specific to Nvidia GPUs ggml changes relating to the ggml tensor library for machine learning labels May 13, 2026
@ggerganov ggerganov added the merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge. label May 13, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ggml changes relating to the ggml tensor library for machine learning merge ready A maintainer can use this label to indicate that they consider the changes final and ready to merge. Nvidia GPU Issues specific to Nvidia GPUs

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants