llama.cpp
CUDA: refactor and optimize IQ MMVQ
#8215
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
6
Changes
View On
GitHub
CUDA: refactor and optimize IQ MMVQ
#8215
JohannesGaessler
merged 6 commits into
ggml-org:master
from
JohannesGaessler:cuda-iq-opt-3
CUDA: refactor and optimize IQ MMVQ
ec15f4d5
github-actions
added
Nvidia GPU
github-actions
added
ggml
uint -> uint32_t
0480dab4
mofosyne
added
Review Complexity : High
__dp4a -> ggml_cuda_dp4a
a92595aa
remove MIN_CC_DP4A checks
78754008
change default
df9e9c9f
slaren
approved these changes on 2024-06-30
try CI fix
30f85eba
JohannesGaessler
merged
cb5fad4c
into master
1 year ago
Login to write a write a comment.
Login via GitHub
Reviewers
slaren
Assignees
No one assigned
Labels
Nvidia GPU
Review Complexity : High
ggml
Milestone
No milestone
Login to write a write a comment.
Login via GitHub