llama.cpp
CUDA: fix crash with partial offloading of MoE
#13439
Merged

CUDA: fix crash with partial offloading of MoE #13439

JohannesGaessler
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
slaren
slaren
JohannesGaessler
JohannesGaessler JohannesGaessler force pushed 328 days ago
JohannesGaessler
slaren
JohannesGaessler CUDA: fix crash with partial offloading of MoE
4bc8f75d
JohannesGaessler JohannesGaessler force pushed to 4bc8f75d 328 days ago
JohannesGaessler
slaren
slaren approved these changes on 2025-05-11
JohannesGaessler JohannesGaessler merged 7474e00b into master 327 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone