tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 11:45:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : drop support for QK_K=64 (#7473)

Browse Source 
* ggml : drop support for QK_K=64

ggml-ci

* opencl : restore QK_K=256 define
This commit is contained in:
Georgi Gerganov
2024-05-23 10:00:21 +03:00
committed by GitHub
parent 1b1e27cb49
commit e84b71c2c6
16 changed files with 26 additions and 4049 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ci/run.sh
View File

@ -606,7 +606,8 @@ if [ -z ${GG_BUILD_LOW_PERF} ]; then
if [ -z ${GG_BUILD_VRAM_GB} ] || [ ${GG_BUILD_VRAM_GB} -ge 8 ]; then
if [ -z ${GG_BUILD_CUDA} ]; then
test $ret -eq 0 && gg_run open_llama_3b_v2
#test $ret -eq 0 && gg_run open_llama_3b_v2
date # dummy
else
test $ret -eq 0 && gg_run open_llama_7b_v2
fi