llama.cpp
CUDA: use 64-bit dst offsets in mul_mat_q
#32374
Merged

CUDA: use 64-bit dst offsets in mul_mat_q #32374

am17an
github-actions github-actions added testing
github-actions github-actions added ggml
github-actions github-actions added CUDA
am17an am17an marked this pull request as ready for review 5 days ago
am17an am17an requested a review from ggerganov ggerganov 5 days ago
am17an am17an requested a review 5 days ago
am17an CUDA: use 64-bit dst offsets in mul_mat_q
3e93391f
am17an am17an force pushed from 30ff7ec5 to 3e93391f 5 days ago
JohannesGaessler
JohannesGaessler approved these changes on 2026-11-17
am17an am17an added merge ready
ggerganov ggerganov merged d4f5c260 into master 2 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone