llama.cpp
CUDA : faster k-quant dot kernels
#1862
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
5
Changes
View On
GitHub
CUDA : faster k-quant dot kernels
#1862
ikawrakow
merged 5 commits into
master
from
ik/cuda-faster-k-quants
cuda : faster k-quant dot kernels
dc67f1a0
ikawrakow
requested a review
from
slaren
2 years ago
ikawrakow
requested a review
from
JohannesGaessler
2 years ago
JohannesGaessler
commented on 2023-06-14
slaren
approved these changes on 2023-06-14
Imrove Q2_K dot kernel on older GPUs
7ced1971
Imrove Q6_K dot kernel on older GPUs
3edee085
Add LLAMA_CUDA_KQUANTS_ITER to CMakeLists.txt and Makefile
31b20758
ggerganov
commented on 2023-06-16
ggerganov
commented on 2023-06-16
PR comments
0dc0b699
ikawrakow
merged
3d011226
into master
2 years ago
ikawrakow
deleted the ik/cuda-faster-k-quants branch
2 years ago
Login to write a write a comment.
Login via GitHub
Reviewers
slaren
ggerganov
JohannesGaessler
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub