llama.cpp
CUDA: non-contiguous (RMS) norm support
#11659
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
5
Changes
View On
GitHub
CUDA: non-contiguous (RMS) norm support
#11659
JohannesGaessler
merged 5 commits into
ggml-org:master
from
JohannesGaessler:cuda-noncont-norm
ggerganov
commented on 2025-02-04
github-actions
added
testing
github-actions
added
Nvidia GPU
github-actions
added
ggml
slaren
approved these changes on 2025-02-04
CUDA: non-contiguous (RMS) norm support
386c52cf
Update ggml/src/ggml-cuda/norm.cu
af7fead9
try CI fix
57d170fb
JohannesGaessler
force pushed
to
57d170fb
318 days ago
try CI fix
a0402ad9
try CI fix
8ef9a5ae
github-actions
added
Vulkan
github-actions
added
Apple Metal
JohannesGaessler
merged
fd08255d
into master
318 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
slaren
ggerganov
Assignees
No one assigned
Labels
testing
Nvidia GPU
Vulkan
ggml
Apple Metal
Milestone
No milestone
Login to write a write a comment.
Login via GitHub