llama.cpp
CUDA: disable cuda graph when using n-cpu-moe
#18593
Merged

CUDA: disable cuda graph when using n-cpu-moe #18593

am17an
am17an CUDA: disable cuda graph when using n-cpu-moe
bda58569
am17an am17an requested a review from JohannesGaessler JohannesGaessler 13 days ago
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
am17an call ggml_cuda_set_device
d91f2f2f
JohannesGaessler
JohannesGaessler approved these changes on 2026-01-04
am17an am17an merged 908a9e5a into master 13 days ago
am17an am17an deleted the cuda-graph-disable-cpu-moe branch 13 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone