Skip to content

Granite MoE NoPE fix #13538

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 14, 2025
Merged

Conversation

gabe-l-hart
Copy link
Contributor

#13269 (comment)

This PR moves the build_inp_pos step to the top of the graph building for consistency with other models while still guarding it behind the use_rope check.

…nite

This matches how others do it, but will still avoid the extra
initialization when rope is disabled.

Branch: GraniteFour

Signed-off-by: Gabe Goodhart <[email protected]>
@ggerganov ggerganov merged commit 5e7d95e into ggml-org:master May 14, 2025
44 checks passed
@gabe-l-hart gabe-l-hart deleted the GraniteMoENopeFix branch May 14, 2025 12:59
Silver267 pushed a commit to Silver267/llama.cpp that referenced this pull request May 14, 2025
…nite (ggml-org#13538)

This matches how others do it, but will still avoid the extra
initialization when rope is disabled.

Branch: GraniteFour

Signed-off-by: Gabe Goodhart <[email protected]>
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