llama.cpp
k_quants tuning for Falcon-7b
#2816
Merged

k_quants tuning for Falcon-7b #2816

ikawrakow merged 2 commits into master from ik/fix_cuda_qkk64
ikawrakow
JohannesGaessler
JohannesGaessler approved these changes on 2023-08-27
Make ggml-cuda.cu build with QK_K = 64
18a131d5
k_quants tuning for Falcon-7b
061f777d
ikawrakow ikawrakow force pushed from f547c585 to 061f777d 2 years ago
ikawrakow ikawrakow changed the title Make ggml-cuda.cu build with QK_K = 64 k_quants tuning for Falcon-7b 2 years ago
ikawrakow ikawrakow marked this pull request as ready for review 2 years ago
klosax
JohannesGaessler
JohannesGaessler
ggerganov
ikawrakow
ikawrakow ikawrakow merged a6d1189f into master 2 years ago
ikawrakow ikawrakow deleted the ik/fix_cuda_qkk64 branch 2 years ago
cebtenzzre
cebtenzzre commented on 2023-09-06

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone