CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: graceful shutdown for Docker images (#10815)

Browse Source
This commit is contained in:
Corentin REGAL
2024-12-13 18:23:50 +01:00
committed by GitHub
parent 4601a8bb67
commit 11e07fd63b
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.devops/tools.sh
View File

@@ -8,11 +8,11 @@ arg1="$1"
shift
if [[ "$arg1" == '--convert' || "$arg1" == '-c' ]]; then
python3 ./convert_hf_to_gguf.py "$@"
exec python3 ./convert_hf_to_gguf.py "$@"
elif [[ "$arg1" == '--quantize' || "$arg1" == '-q' ]]; then
./llama-quantize "$@"
exec ./llama-quantize "$@"
elif [[ "$arg1" == '--run' || "$arg1" == '-r' ]]; then
./llama-cli "$@"
exec ./llama-cli "$@"
elif [[ "$arg1" == '--all-in-one' || "$arg1" == '-a' ]]; then
echo "Converting PTH to GGML..."
for i in `ls $1/$2/ggml-model-f16.bin*`; do
@@ -20,11 +20,11 @@ elif [[ "$arg1" == '--all-in-one' || "$arg1" == '-a' ]]; then
echo "Skip model quantization, it already exists: ${i/f16/q4_0}"
else
echo "Converting PTH to GGML: $i into ${i/f16/q4_0}..."
./llama-quantize "$i" "${i/f16/q4_0}" q4_0
exec ./llama-quantize "$i" "${i/f16/q4_0}" q4_0
fi
done
elif [[ "$arg1" == '--server' || "$arg1" == '-s' ]]; then
./llama-server "$@"
exec ./llama-server "$@"
else
echo "Unknown command: $arg1"
echo "Available commands: "