llama.cpp
ggml: add ggml_can_fuse_subgraph
#16662
Merged

ggml: add ggml_can_fuse_subgraph #16662

am17an
am17an am17an requested a review from ggerganov ggerganov 217 days ago
am17an am17an requested a review from slaren slaren 217 days ago
am17an am17an marked this pull request as draft 217 days ago
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
am17an am17an changed the title Ggml can fuse subgraph ggml: add ggml_can_fuse_subgraph 217 days ago
am17an am17an requested a review from jeffbolznv jeffbolznv 217 days ago
am17an ggml: add ggml_can_fuse_subgraph
b8a3661a
am17an ggml-cuda: use ggml_can_fuse_subgraph for topk-moe
578d918e
am17an format
ba472d1a
jeffbolznv
am17an
jeffbolznv
jeffbolznv commented on 2025-10-20
jeffbolznv
am17an 1. remove inputs from signature as they are transient nodes
d8530364
am17an am17an force pushed to d8530364 215 days ago
am17an
am17an commented on 2025-10-20
jeffbolznv
jeffbolznv commented on 2025-10-20
am17an - combine check into one loop
977a3333
jeffbolznv
jeffbolznv
jeffbolznv commented on 2025-10-21
jeffbolznv
jeffbolznv approved these changes on 2025-10-21
am17an remove redudant if test
c1054d53
am17an am17an marked this pull request as ready for review 215 days ago
jeffbolznv
jeffbolznv approved these changes on 2025-10-21
ggerganov
ggerganov approved these changes on 2025-10-21
am17an - rename and other minor review comments
3886b5f1
am17an add assert about count < 32
f2cdb32b
am17an am17an requested a review from jeffbolznv jeffbolznv 215 days ago
am17an am17an requested a review from ggerganov ggerganov 215 days ago
am17an
am17an am17an merged 4926419c into master 215 days ago
am17an am17an deleted the ggml_can_fuse_subgraph branch 215 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone