Move pipeline directory

This commit is contained in:
Aaron Po
2026-04-27 16:00:55 -04:00
parent 5a21589029
commit 9ed37806dd
80 changed files with 0 additions and 0 deletions

View File

@@ -0,0 +1,181 @@
cmake_minimum_required(VERSION 3.24)
project(biergarten-pipeline)
set(CMAKE_POLICY_VERSION_MINIMUM 3.5 CACHE STRING "" FORCE)
# =============================================================================
# 1. Platform & GPU Detection
# =============================================================================
if(WIN32)
message(FATAL_ERROR "[biergarten] Windows is currently not supported. Please use Linux (Fedora 43) or macOS (M1 Pro).")
endif()
if(APPLE)
if(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64")
message(STATUS "[biergarten] Apple Silicon detected — enabling Metal acceleration.")
set(GGML_METAL ON CACHE BOOL "Enable Metal for Apple Silicon" FORCE)
else()
message(STATUS "[biergarten] Intel Mac detected — using CPU / Accelerate framework.")
set(GGML_METAL OFF CACHE BOOL "Disable Metal for Intel Macs" FORCE)
endif()
elseif(UNIX AND NOT APPLE)
find_package(CUDAToolkit QUIET)
find_package(HIP QUIET)
if(CUDAToolkit_FOUND)
message(STATUS "[biergarten] NVIDIA GPU detected — enabling CUDA acceleration.")
set(GGML_CUDA ON CACHE BOOL "Enable CUDA for NVIDIA GPUs" FORCE)
set(CMAKE_CUDA_ARCHITECTURES native)
elseif(HIP_FOUND OR EXISTS "/opt/rocm")
message(STATUS "[biergarten] AMD GPU detected — enabling HIP/ROCm acceleration.")
set(GGML_HIPBLAS ON CACHE BOOL "Enable HIP for AMD GPUs" FORCE)
else()
message(STATUS "[biergarten] No NVIDIA or AMD GPU found — falling back to CPU.")
endif()
endif()
# =============================================================================
# 2. Project-wide Settings (Standard & Optimization)
# =============================================================================
set(CMAKE_CXX_STANDARD 20)
set(CMAKE_CXX_STANDARD_REQUIRED ON)
set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
# Release Build Optimization: Aggressive (-O3), Arch-specific, and LTO
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -O3 -march=native -flto")
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -Og -g")
# =============================================================================
# 3. Dependencies
# =============================================================================
include(FetchContent)
find_package(CURL QUIET)
if(NOT CURL_FOUND)
message(FATAL_ERROR "[biergarten] libcurl not found. Install it (e.g. 'sudo dnf install libcurl-devel').")
endif()
# Require system Boost for JSON and Program Options to speed up build times
find_package(Boost REQUIRED COMPONENTS json program_options)
FetchContent_Declare(
sqlite_amalgamation
URL https://www.sqlite.org/2026/sqlite-amalgamation-3530000.zip
URL_HASH SHA3_256=c2325c53b3b41761469f91cfb078e96882ac5d85bac10c11b0bd8f253b031e5b
)
FetchContent_GetProperties(sqlite_amalgamation)
if(NOT sqlite_amalgamation_POPULATED)
FetchContent_Populate(sqlite_amalgamation)
endif()
if(NOT TARGET sqlite3)
add_library(sqlite3 STATIC
${sqlite_amalgamation_SOURCE_DIR}/sqlite3.c
)
target_include_directories(sqlite3 PUBLIC
${sqlite_amalgamation_SOURCE_DIR}
)
target_compile_definitions(sqlite3 PUBLIC
SQLITE_THREADSAFE=1
)
endif()
FetchContent_Declare(
llama-cpp
GIT_REPOSITORY https://github.com/ggml-org/llama.cpp.git
GIT_TAG b8742
)
FetchContent_MakeAvailable(llama-cpp)
FetchContent_Declare(
boost-di
GIT_REPOSITORY https://github.com/boost-ext/di.git
GIT_TAG v1.3.0
)
FetchContent_MakeAvailable(boost-di)
if(TARGET Boost.DI AND NOT TARGET boost::di)
add_library(boost::di ALIAS Boost.DI)
endif()
FetchContent_Declare(
spdlog
GIT_REPOSITORY https://github.com/gabime/spdlog.git
GIT_TAG v1.15.3
)
FetchContent_MakeAvailable(spdlog)
# =============================================================================
# 4. Sources
# =============================================================================
set(SOURCES
src/main.cc
src/biergarten_data_generator/biergarten_data_generator.cc
src/biergarten_data_generator/run.cc
src/biergarten_data_generator/query_cities_with_countries.cc
src/biergarten_data_generator/generate_breweries.cc
src/biergarten_data_generator/log_results.cc
src/services/wikipedia/wikipedia_service.cc
src/services/wikipedia/get_summary.cc
src/services/wikipedia/fetch_extract.cc
src/services/sqlite/sqlite_export_service.cc
src/services/sqlite/build_database_path.cc
src/services/sqlite/build_location_key.cc
src/services/sqlite/initialize_schema.cc
src/services/sqlite/prepare_statements.cc
src/services/sqlite/initialize.cc
src/services/sqlite/process_record.cc
src/services/sqlite/finalize_statements.cc
src/services/sqlite/rollback_and_close_no_throw.cc
src/services/sqlite/finalize.cc
src/web_client/curl_global_state.cc
src/web_client/curl_web_client_get.cc
src/web_client/curl_web_client_url_encode.cc
src/data_generation/llama/llama_generator.cc
src/data_generation/llama/generate_brewery.cc
src/data_generation/llama/generate_user.cc
src/data_generation/llama/helpers.cc
src/data_generation/llama/infer.cc
src/data_generation/llama/load.cc
src/data_generation/llama/load_brewery_prompt.cc
src/data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.cc
src/data_generation/mock/deterministic_hash.cc
src/data_generation/mock/generate_brewery.cc
src/data_generation/mock/generate_user.cc
src/json_handling/json_loader.cc
)
# =============================================================================
# 5. Target
# =============================================================================
add_executable(${PROJECT_NAME} ${SOURCES})
target_include_directories(${PROJECT_NAME} PRIVATE
includes
${llama-cpp_SOURCE_DIR}/include
${llama-cpp_SOURCE_DIR}/common
)
target_link_libraries(${PROJECT_NAME} PRIVATE
llama
boost::di
Boost::json
Boost::program_options
spdlog::spdlog
sqlite3
CURL::libcurl
)
# =============================================================================
# 6. Runtime Assets
# =============================================================================
configure_file(
${CMAKE_SOURCE_DIR}/locations.json
${CMAKE_BINARY_DIR}/locations.json
COPYONLY
)
add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
COMMAND ${CMAKE_COMMAND} -E copy_directory
${CMAKE_SOURCE_DIR}/prompts
${CMAKE_BINARY_DIR}/prompts
)