llama.cpp
ggml: avoid creating CUDA context during device init
#20595
Merged
Overview
Commits
1
Changes
View On GitHub

ggml: avoid creating CUDA context during device init #20595

am17an merged 1 commit into ggml-org:master from ServeurpersoCom:cuda-defer-context-init
ServeurpersoCom
ServeurpersoCom ggml: avoid creating CUDA context during device init
15f4c938
ServeurpersoCom ServeurpersoCom requested a review 21 days ago
am17an
ServeurpersoCom
am17an
am17an approved these changes on 2026-03-15
JohannesGaessler
JohannesGaessler approved these changes on 2026-03-15
tehsiuhuang
ServeurpersoCom
ServeurpersoCom
tehsiuhuang
am17an am17an merged ceef6b52 into master 21 days ago
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Nvidia GPU ggml
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum