CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update server-llm.sh

Browse Source
This commit is contained in:
Olivier Chafik
2024-06-07 11:52:40 +01:00
parent af8f0169da
commit 0dba58269f
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
scripts/server-llm.sh
View File

@@ -380,13 +380,13 @@ fi
if [[ "$backend" == "cuda" ]]; then
printf "[+] Building with CUDA backend\n"
LLAMA_CUDA=1 make -j server $log
LLAMA_CUDA=1 make -j llama-server $log
elif [[ "$backend" == "cpu" ]]; then
printf "[+] Building with CPU backend\n"
make -j server $log
make -j llama-server $log
elif [[ "$backend" == "metal" ]]; then
printf "[+] Building with Metal backend\n"
make -j server $log
make -j llama-server $log
else
printf "[-] Unknown backend: %s\n" "$backend"
exit 1
@@ -413,6 +413,6 @@ if [[ $verbose -eq 1 ]]; then
args="$args --verbose"
fi
./server -m "../$wfile" --host 0.0.0.0 --port "$port" -c $n_kv -np "$n_parallel" $args
./llama-server -m "../$wfile" --host 0.0.0.0 --port "$port" -c $n_kv -np "$n_parallel" $args
exit 0