llama.cpp
CUDA, Fix CI: split the PAD_REFLECT_1D grid to stay within the HIP grid limit
#32179
Merged

CUDA, Fix CI: split the PAD_REFLECT_1D grid to stay within the HIP grid limit #32179

ServeurpersoCom
ServeurpersoCom CUDA: split the PAD_REFLECT_1D grid to stay within the HIP grid limit
ff0e760c
ServeurpersoCom ServeurpersoCom requested a review 1 day ago
github-actions github-actions added ggml
github-actions github-actions added CUDA
danbev
danbev approved these changes on 2026-11-13
am17an
am17an approved these changes on 2026-11-13
ServeurpersoCom
ServeurpersoCom
IMbackK
IMbackK approved these changes on 2026-11-13
IMbackK
ggerganov ggerganov merged 2d8a3250 into master 1 day ago
ggerganov
ggerganov

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone