llama.cpp
CUDA: fix overflow in FA, tune performance
#14840
Merged

CUDA: fix overflow in FA, tune performance #14840

JohannesGaessler
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
slaren
slaren approved these changes on 2025-07-23
ggerganov
ggerganov commented on 2025-07-23
JohannesGaessler CUDA: fix overflow in FA, tune performance
d4209ee4
JohannesGaessler JohannesGaessler force pushed from ec05b081 to d4209ee4 48 days ago
ggerganov
ggerganov approved these changes on 2025-07-23
JohannesGaessler JohannesGaessler merged a86f52b2 into master 48 days ago
he29-net
JohannesGaessler
he29-net
he29-net

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone