Skip to content

Granite MoE NoPE fix#13538

Merged
ggerganov merged 1 commit intoggml-org:masterfrom
gabe-l-hart:GraniteMoENopeFix
May 14, 2025
Merged

Granite MoE NoPE fix#13538
ggerganov merged 1 commit intoggml-org:masterfrom
gabe-l-hart:GraniteMoENopeFix

Conversation

@gabe-l-hart
Copy link
Collaborator

#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 <ghart@us.ibm.com>
@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 <ghart@us.ibm.com>
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