#!/usr/bin/env bash
# ==============================================================================
# Build script for compiling llama.cpp with NVIDIA NCCL tensor parallelism
# Optimized for Turing GPUs (RTX 2060, CMP 50HX, sm_75)
# ==============================================================================
set -euo pipefail

LLAMA_DIR="${1:-/opt/llama.cpp}"
BUILD_DIR="${LLAMA_DIR}/build-nccl"

echo "==> Ensuring build dependencies are installed..."
apt-get update -qq && apt-get install -y -qq \
    build-essential cmake git ninja-build \
    libcurl4-openssl-dev libssl-dev pkg-config

echo "==> Configuring CMake for llama.cpp with NCCL and CUDA sm_75..."
mkdir -p "$BUILD_DIR"
cd "$BUILD_DIR"

cmake .. \
    -GNinja \
    -DGGML_CUDA=ON \
    -DGGML_CUDA_GRAPHS=ON \
    -DGGML_CUDA_FORCE_CUBLAS=ON \
    -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 \
    -DGGML_CUDA_ARCHITECTURES="75" \
    -DCMAKE_BUILD_TYPE=Release

echo "==> Building llama-server..."
ninja llama-server

echo "==> Build complete! Binary located at: ${BUILD_DIR}/bin/llama-server"