llama.cpp
CUDA: refactor mmq, dmmv, mmvq
#7716
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
5
Changes
View On
GitHub
CUDA: refactor mmq, dmmv, mmvq
#7716
JohannesGaessler
merged 5 commits into
ggml-org:master
from
JohannesGaessler:deduplicate-mmq-12
CUDA: refactor mmq, dmmv, mmvq
158e3d3e
slaren
commented on 2024-06-03
github-actions
added
build
github-actions
added
Nvidia GPU
github-actions
added
python
github-actions
added
ggml
fix out-of-bounds write
bd8422db
struct for qk, qr, qi
8b6962dd
JohannesGaessler
force pushed
from
79d415d5
to
8b6962dd
1 year ago
fix cmake build
fe1c4bbf
slaren
approved these changes on 2024-06-04
mofosyne
added
refactoring
mofosyne
added
Review Complexity : High
mmq_type_traits
fd65ff31
JohannesGaessler
merged
7d1a378b
into master
1 year ago
Login to write a write a comment.
Login via GitHub
Reviewers
slaren
Assignees
No one assigned
Labels
build
refactoring
Nvidia GPU
python
Review Complexity : High
ggml
Milestone
No milestone
Login to write a write a comment.
Login via GitHub