File size: 425 Bytes
56e9d7e
 
 
 
aee66c6
 
56e9d7e
 
 
 
aee66c6
56e9d7e
 
aee66c6
 
56e9d7e
aee66c6
 
381b08a
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
#!/bin/bash
set -e

echo "Starting llama.cpp server..."
# The binary is located at /app/llama-server in the ggml-org/llama.cpp image
/app/llama-server \
  -m /app/SmolLM2-1.7B-Instruct-Q4_K_M.gguf \
  --host 0.0.0.0 \
  --port 8080 \
  -t 2 \
  -c 2048 \
  --log-disable &

echo "Waiting for server to initialize..."
sleep 10

echo "Starting Gradio App..."
# Explicitly use the venv's python
/opt/venv/bin/python3 /app/app.py