File size: 444 Bytes
27f2cfd
 
 
 
b796c25
 
 
 
 
 
27f2cfd
 
 
 
b796c25
27f2cfd
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
#!/bin/bash

# Start llama-server in background
cd /llama.cpp/build
./bin/llama-server \
    --host 0.0.0.0 \
    --port 8080 \
    --model /models/model.gguf \
    --ctx-size 32768 \
    --threads $(nproc) &

# Wait for server to initialize
echo "Waiting for server to start..."
until curl -s "http://localhost:8080/v1/models" >/dev/null; do
    sleep 2
done

echo "Server is ready. Starting Gradio app."

# Start Gradio UI
cd /
python3 app.py