File size: 338 Bytes
4bdb245
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
#!/bin/sh

# For mlock 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