llama.cpp
metal: optimise `GGML_OP_SUM`
#16559
Merged

metal: optimise `GGML_OP_SUM` #16559

cern1710
cern1710 optimise GGML_OP_SUM
9cc51d39
cern1710 cern1710 requested a review from ggerganov ggerganov 159 days ago
github-actions github-actions added ggml
github-actions github-actions added Apple Metal
ggerganov
cern1710 add non-contiguous tests by permuting the input
4619142b
cern1710 cern1710 requested a review from slaren slaren 159 days ago
github-actions github-actions added testing
cern1710 change tests to require full contiguity of OP_SUM
c25a6c7c
cern1710
ggerganov
ggerganov
ggerganov approved these changes on 2025-10-14
ggerganov
cern1710
ggerganov cuda : add check GGML_OP_SUM
be1b6703
ggerganov ggerganov merged f4ce81c4 into master 157 days ago
github-actions github-actions added Nvidia GPU
JulianPscheid
ggerganov
JulianPscheid

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone