llama.cpp
llama: copy tensor_split at model load instead of retaining caller pointer, resolving segfault
#24552
Open
Open
llama: copy tensor_split at model load instead of retaining caller pointer, resolving segfault #24552
dragonfyre13
wants to merge
1 commit into
ggml-org:master
from
dragonfyre13:pr/tensor-split-ownership
Copy tensor_split into model-owned storage
2124a94b
Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub