llama.cpp
ggml : use WARP_SIZE/2 for argmax reduction offset
#18092

Merged

ggml : use WARP_SIZE/2 for argmax reduction offset #18092

am17an merged 1 commit into ggml-org:master from Aadeshveer:ggml-fix-argmax-offset

ggml : use WARP_SIZE/2 for argmax reduction offset

c2f3f7a2

am17an approved these changes on 2025-12-16

github-actions added Nvidia GPU

github-actions added ggml

JohannesGaessler approved these changes on 2025-12-16

am17an merged 58062860 into master 176 days ago

Reviewers

JohannesGaessler

am17an

Assignees

No one assigned

Labels

Nvidia GPU ggml

Milestone

No milestone