#!/usr/bin/env bash
# ==============================================================================
# Production startup script for llama-server with NCCL tensor parallelism
# Supports: 256K Context Window, Multimodal Vision Projector, Flash Attention,
#           q4_0 KV Cache quantization, and Jinja reasoning control.
# ==============================================================================
set -euo pipefail

MODEL_PATH="${MODEL_PATH:-/opt/models/gguf/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf}"
MMPROJ_PATH="${MMPROJ_PATH:-/opt/models/gguf/mmproj-Qwen3.8-27B-Uncensored-f16.gguf}"
BINARY="${LLAMA_BINARY:-/opt/llama.cpp/build-nccl/bin/llama-server}"

export LD_LIBRARY_PATH="/opt/llama.cpp/build-nccl/bin:/opt/minicpm-venv/lib/python3.13/site-packages/nvidia/nccl/lib:/lib/x86_64-linux-gnu:${LD_LIBRARY_PATH:-}"

exec "$BINARY" \
  -m "$MODEL_PATH" \
  --mmproj "$MMPROJ_PATH" \
  -ngl 99 \
  -c 262144 \
  --parallel 1 \
  --image-max-tokens 2048 \
  --split-mode tensor \
  --flash-attn on \
  --batch-size 1024 \
  --ubatch-size 256 \
  --jinja \
  --threads 12 \
  --cache-type-k q4_0 \
  --cache-type-v q4_0 \
  --host 0.0.0.0 \
  --port 8080