llama.cpp
CUDA: make the alloc_deps check batch independent
#29986

Merged

CUDA: make the alloc_deps check batch independent #29986

am17an merged 1 commit into master from aman/cuda-fix-graph-realloc

CUDA: make the alloc_deps check batch independent

9f80c69e

am17an requested a review 38 days ago

github-actions added ggml

github-actions added CUDA

ggerganov approved these changes on 2026-10-05

ServeurpersoCom approved these changes on 2026-10-05

am17an merged e117148a into master 38 days ago

Reviewers

ServeurpersoCom

ggerganov

Assignees

No one assigned

Labels

ggml CUDA

Milestone

No milestone