huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

misc(ci): let's actually setup sccache in the build.rs

Browse Source
This commit is contained in:
Morgan Funtowicz 2025-01-09 00:03:29 +01:00
parent df9df1d37c
commit a7a7c67d6e
2 changed files with 117 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
backends/trtllm/CMakeLists.txt
View File

@ -76,7 +76,10 @@ target_link_libraries(tgi_trtllm_backend_impl PRIVATE tensorrt_llm nvinfer_plugi
install(TARGETS tgi_trtllm_backend_impl)
install(TARGETS tensorrt_llm nvinfer_plugin_tensorrt_llm decoder_attention executorWorker)
install(FILES ${TRTLLM_NVRTC_WRAPPER_LIBRARY_PATH} TYPE LIB)
install(FILES ${TRTLLM_EXECUTOR_STATIC_LIBRARY_PATH} TYPE LIB)
if (NOT ${TGI_TRTLLM_BACKEND_DEBUG})
install(FILES ${TRTLLM_EXECUTOR_STATIC_LIBRARY_PATH} TYPE LIB)
endif ()
#### Unit Tests ####
if (${TGI_TRTLLM_BACKEND_BUILD_TESTS})
@ -122,13 +125,10 @@ if (${TGI_TRTLLM_BACKEND_BUILD_TESTS})
endif ()
endif ()
if(CMAKE_BUILD_TYPE MATCHES "Debug")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Werror -fsanitize=undefined -fsanitize=address")
target_link_options(tgi_trtllm_backend_tests BEFORE PUBLIC -fsanitize=undefined PUBLIC -fsanitize=address)
endif()
install(TARGETS tgi_trtllm_backend_tests)
list(APPEND CMAKE_MODULE_PATH ${catch2_SOURCE_DIR}/extras)
include(CTest)
include(Catch)
catch_discover_tests(tgi_trtllm_backend_tests)
endif ()
# list(APPEND CMAKE_MODULE_PATH ${catch2_SOURCE_DIR}/extras)
# include(CTest)
# include(Catch)
# catch_discover_tests(tgi_trtllm_backend_tests)
endif ()

129
backends/trtllm/build.rs
View File

@ -3,6 +3,7 @@ use pkg_config;
use std::env;
use std::env::consts::ARCH;
use std::path::{absolute, PathBuf};
use std::sync::LazyLock;
const ADDITIONAL_BACKEND_LINK_LIBRARIES: [&str; 1] = ["spdlog"];
const CUDA_ARCH_LIST: Option<&str> = option_env!("CUDA_ARCH_LIST");
@ -12,12 +13,20 @@ const INSTALL_PREFIX: Option<&str> = option_env!("CMAKE_INSTALL_PREFIX");
const TENSORRT_ROOT_DIR: Option<&str> = option_env!("TENSORRT_ROOT_DIR");
const NCCL_ROOT_DIR: Option<&str> = option_env!("NCCL_ROOT_DIR");
const IS_GHA_BUILD: LazyLock<bool> = LazyLock::new(|| {
option_env!("IS_GHA_BUILD").map_or(false, |value| match value.to_lowercase().as_str() {
"on" => true,
"true" => true,
"1" => true,
_ => false,
})
});
// Dependencies
const BACKEND_DEPS: [&str; 2] = ["tgi_trtllm_backend_impl", "tgi_trtllm_backend"];
const BACKEND_DEPS: &str = "tgi_trtllm_backend_impl";
const CUDA_TRANSITIVE_DEPS: [&str; 4] = ["cuda", "cudart", "cublas", "nvidia-ml"];
const TENSORRT_LLM_TRANSITIVE_DEPS: [(&str, &str); 5] = [
const TENSORRT_LLM_TRANSITIVE_DEPS: [(&str, &str); 4] = [
("dylib", "tensorrt_llm"),
("static", "tensorrt_llm_executor_static"),
("dylib", "tensorrt_llm_nvrtc_wrapper"),
("dylib", "nvinfer_plugin_tensorrt_llm"),
("dylib", "decoder_attention"),
@ -32,6 +41,48 @@ macro_rules! probe {
};
}
fn get_compiler_flag(
switch: bool,
true_case: &'static str,
false_case: &'static str,
) -> &'static str {
match switch {
true => true_case,
false => false_case,
}
}
fn get_library_architecture() -> &'static str {
let os = env::var("CARGO_CFG_TARGET_OS").unwrap();
let arch = env::var("CARGO_CFG_TARGET_ARCH").unwrap();
let env = env::var("CARGO_CFG_TARGET_ENV").unwrap();
match os.as_str() {
"linux" => {
if env != "gnu" {
panic!("unsupported linux ABI {env}, only 'gnu' is supported")
}
match arch.as_str() {
"x86_64" => "x86_64-linux-gnu",
"aarch64" => "aarch64-linux-gnu",
_ => panic!("unsupported linux architecture {arch}"),
}
}
"windows" => {
if env != "msvc" {
panic!("unsupported windows ABI {env}, only 'msvc' is supported")
}
match arch.as_str() {
"x86_64" => "x86_64-windows-msvc",
_ => panic!("unsupported windows architecture {arch}"),
}
}
_ => panic!("unsupported OS {os}"),
}
}
fn build_backend(is_debug: bool, opt_level: &str, out_dir: &PathBuf) -> (PathBuf, PathBuf) {
// Build the backend implementation through CMake
let install_path = INSTALL_PREFIX.unwrap_or("/usr/local/tgi");
@ -54,10 +105,48 @@ fn build_backend(is_debug: bool, opt_level: &str, out_dir: &PathBuf) -> (PathBuf
.env("OPT_LEVEL", opt_level)
.define("CMAKE_INSTALL_PREFIX", &install_path)
.define("CMAKE_CUDA_COMPILER", "/usr/local/cuda/bin/nvcc")
.define("Python3_ROOT_DIR", "../venv")
.define("CMAKE_LIBRARY_ARCHITECTURE", get_library_architecture())
.define("TGI_TRTLLM_BACKEND_TARGET_CUDA_ARCH_LIST", cuda_arch_list)
.define(
"TGI_TRTLLM_BACKEND_DEBUG",
get_compiler_flag(is_debug, "ON", "OFF"),
)
.define("TGI_TRTLLM_BACKEND_TRT_ROOT", tensorrt_path);
if is_debug {
config.define("TGI_TRTLLM_BACKEND_BUILD_TESTS", "ON");
}
if let Some(wrapper) = option_env!("RUSTC_WRAPPER") {
if wrapper == "sccache" {
println!("cargo:warning=Using caching tool: {wrapper}");
config.define("CMAKE_CXX_COMPILER_LAUNCHER", wrapper);
}
}
if option_env!("USE_LLD_LINKER").is_some() {
println!("cargo:warning=Using lld linker");
config.define("TGI_TRTLLM_BACKEND_BUILD_USE_LLD", "ON");
}
if (is_debug && option_env!("ENABLE_ASAN").is_some()) || *IS_GHA_BUILD {
println!("cargo:warning=Enabling Address Sanitizer");
config.define("TGI_TRTLLM_BACKEND_ENABLE_ASAN", "ON");
}
if (is_debug && option_env!("ENABLE_UBSAN").is_some()) || *IS_GHA_BUILD {
println!("cargo:warning=Enabling Undefined Sanitizer");
config.define("TGI_TRTLLM_BACKEND_ENABLE_UBSAN", "ON");
}
if let Some(nvcc_host_compiler) = option_env!("CMAKE_CUDA_HOST_COMPILER") {
config.define("CMAKE_CUDA_HOST_COMPILER", nvcc_host_compiler);
}
if let Some(cxx_compiler_launcher) = option_env!("CMAKE_CXX_COMPILER_LAUNCHER") {
config.define("CMAKE_CXX_COMPILER_LAUNCHER", cxx_compiler_launcher);
}
// Allow to override which Python to use ...
if let Some(python3) = option_env!("Python3_EXECUTABLE") {
config.define("Python3_EXECUTABLE", python3);
@ -78,23 +167,18 @@ fn build_backend(is_debug: bool, opt_level: &str, out_dir: &PathBuf) -> (PathBuf
}
// Emit linkage information from the artifacts we just built
let install_lib_path = install_path.join("lib");
println!(
r"cargo:warning=Adding link search path: {}",
install_lib_path.display()
);
println!(r"cargo:rustc-link-search={}", install_lib_path.display());
for path in ["lib", "lib64"] {
let install_lib_path = install_path.join(path);
println!(
r"cargo:warning=Adding link search path: {}",
install_lib_path.display()
);
println!(r"cargo:rustc-link-search={}", install_lib_path.display());
}
(PathBuf::from(install_path), deps_folder)
}
fn build_ffi_layer(deps_folder: &PathBuf, is_debug: bool) {
let ndebug = match is_debug {
true => "1",
false => "0",
};
CFG.include_prefix = "backends/trtllm";
cxx_build::bridge("src/lib.rs")
.static_flag(true)
@ -106,7 +190,10 @@ fn build_ffi_layer(deps_folder: &PathBuf, is_debug: bool) {
.include("/usr/local/tensorrt/include")
.include("csrc/")
.file("csrc/ffi.hpp")
.define("TGI_TRTLLM_BACKEND_DEBUG", ndebug)
.define(
"TGI_TRTLLM_BACKEND_DEBUG",
get_compiler_flag(is_debug, "ON", "OFF"),
)
.compile("tgi_trtllm_backend");
println!("cargo:rerun-if-changed=CMakeLists.txt");
@ -161,7 +248,5 @@ fn main() {
});
// Backend
BACKEND_DEPS.iter().for_each(|name| {
println!("cargo:rustc-link-lib=static={}", name);
});
}
println!("cargo:rustc-link-lib=static={}", &BACKEND_DEPS);
}