llama.cpp
CUDA: check for buffer overlap before fusing
#21566
Merged

CUDA: check for buffer overlap before fusing #21566

am17an
am17an CUDA: check for buffer overlap before fusing
fc889c19
am17an am17an requested a review 58 days ago
am17an
ggerganov
JohannesGaessler
JohannesGaessler commented on 2026-04-07
JohannesGaessler
ggerganov
ggerganov commented on 2026-04-07
ggerganov
pwilkin
am17an use ggml_cuda_check_fusion_memory_ranges
04e27cf8
am17an
JohannesGaessler
JohannesGaessler approved these changes on 2026-04-07
pwilkin
ggerganov
ggerganov approved these changes on 2026-04-07
am17an am17an merged de1aa6fa into master 58 days ago
am17an am17an deleted the cuda_fix_buffer_overlap branch 58 days ago
ORippler
danielhanchen
EthanBlazkowicz
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
am17an

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone