llama.cpp
CUDA: Implemented row flattening for non-glm RoPE
#2468

Merged

CUDA: Implemented row flattening for non-glm RoPE #2468

JohannesGaessler merged 1 commit into ggml-org:master from JohannesGaessler:cuda-flatten-rope

CUDA: Implemented row flattening for non-glm RoPE

58ff5e17

slaren approved these changes on 2023-07-31

JohannesGaessler merged 1215ed7d into master 2 years ago

Reviewers

slaren

Assignees

No one assigned

Labels

None yet

Milestone

No milestone