llama.cpp
ggml : allow CUDA graphs when using pipeline parallelism
#13814

Merged

ggml : allow CUDA graphs when using pipeline parallelism #13814

slaren merged 1 commit into master from sl/fix-cuda-graphs-pp

ggml : allow CUDA graphs when using pipeline parallelism

c17627c8

github-actions added ggml

ggerganov approved these changes on 2025-05-27

slaren merged 952f3953 into master 1 year ago

slaren deleted the sl/fix-cuda-graphs-pp branch 1 year ago

Reviewers

ggerganov

Assignees

No one assigned

Labels

ggml

Milestone

No milestone