llama.cpp
CUDA: fix padding of GQA to power of 2 in FA
#19115
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
1
Changes
View On
GitHub
CUDA: fix padding of GQA to power of 2 in FA
#19115
JohannesGaessler
merged 1 commit into
ggml-org:master
from
JohannesGaessler:cuda-fa-fix-gqa-padding
CUDA: fix padding of GQA to power of 2 in FA
060a6944
JohannesGaessler
requested a review
from
ggerganov
189 days ago
github-actions
added
testing
github-actions
added
Nvidia GPU
github-actions
added
ggml
ggerganov
approved these changes on 2026-01-26
JohannesGaessler
merged
b0311c16
into master
188 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
ggerganov
Assignees
No one assigned
Labels
testing
Nvidia GPU
ggml
Milestone
No milestone
Login to write a write a comment.
Login via GitHub