thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

ci, tests : use cmake to download models and remove libcurl dependency (#18791)

Browse source 
* ci, tests : use cmake to download models and remove libcurl dependency
* llama_dl_model -> llama_download_model
* use EXPECTED_HASH for robust model downloading
* Move llama_download_model to cmake/common.cmake

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët 2026-01-14 07:46:27 +01:00 • committed by GitHub
parent 6e36299b47
commit f709c7a33f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 41 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ci/run.sh
View file

@ -45,7 +45,7 @@ sd=`dirname $0`
cd $sd/../
SRC=`pwd`
CMAKE_EXTRA="-DLLAMA_FATAL_WARNINGS=${LLAMA_FATAL_WARNINGS:-ON} -DLLAMA_CURL=ON -DGGML_SCHED_NO_REALLOC=ON"
CMAKE_EXTRA="-DLLAMA_FATAL_WARNINGS=${LLAMA_FATAL_WARNINGS:-ON} -DLLAMA_CURL=OFF -DGGML_SCHED_NO_REALLOC=ON"
if [ ! -z ${GG_BUILD_METAL} ]; then
CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_METAL=ON"