llama.cpp/docker/start_server.sh
2023-05-23 19:26:40 +00:00

11 lines
337 B
Bash
Executable file

#!/bin/sh
# For mmap support
ulimit -l unlimited
if [ "$IMAGE" = "python:3-slim-bullseye" ]; then
python3 -B -m llama_cpp.server --model /app/model.bin
else
# You may have to reduce --n_gpu_layers=1000 to 20 or less if you don't have enough VRAM
python3 -B -m llama_cpp.server --model /app/model.bin --n_gpu_layers=1000
fi