#!/bin/bash
# Starts the llama-server that voice-bench.html talks to.
#
# Requires:
#   - llama.cpp built with CUDA support (see README.md)
#   - the Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf file (from the team
#     Google Drive)
#
# Configure by setting environment variables before running, e.g.:
#   MODEL_PATH=/data/models/Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf \
#   LLAMA_SERVER=/opt/llama.cpp/build/bin/llama-server \
#   ./start-model.sh
# or just edit the defaults below.
set -e

MODEL_PATH="${MODEL_PATH:-$HOME/models/Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf}"
LLAMA_SERVER="${LLAMA_SERVER:-$HOME/llama.cpp/build/bin/llama-server}"
HOST="${HOST:-0.0.0.0}"
PORT="${PORT:-8200}"
CTX_SIZE="${CTX_SIZE:-32768}"

if [ ! -f "$MODEL_PATH" ]; then
  echo "!!! Model not found at: $MODEL_PATH"
  echo "    Download it from the team Google Drive, then either place it at"
  echo "    that path or re-run with MODEL_PATH=/path/to/the/file.gguf"
  exit 1
fi
if [ ! -x "$LLAMA_SERVER" ]; then
  echo "!!! llama-server not found/executable at: $LLAMA_SERVER"
  echo "    Build llama.cpp first -- see README.md -- or re-run with"
  echo "    LLAMA_SERVER=/path/to/llama-server"
  exit 1
fi

echo "Model:  $MODEL_PATH"
echo "Server: $LLAMA_SERVER"
echo "Listening on ${HOST}:${PORT}, context ${CTX_SIZE}"
echo "(if this exits with an out-of-memory error, re-run with a smaller CTX_SIZE, e.g. CTX_SIZE=8192)"
echo

exec "$LLAMA_SERVER" \
  --model "$MODEL_PATH" \
  --host "$HOST" \
  --port "$PORT" \
  -ngl 999 \
  --ctx-size "$CTX_SIZE" \
  --threads 8