huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-25 03:52:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(backend): allow overriding which Python to use

Browse Source
This commit is contained in:
Morgan Funtowicz 2024-12-02 15:08:34 +01:00
parent 71e700a6ea
commit 879e1a4178
2 changed files with 15 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
backends/trtllm/build.rs
View File

@ -43,8 +43,8 @@ fn build_backend(is_debug: bool, opt_level: &str, out_dir: &PathBuf) -> (PathBuf
install_path = absolute(out_dir).expect("cannot happen").join(install_path); install_path = absolute(out_dir).expect("cannot happen").join(install_path);
} }
let _ = cmake::Config::new(".") let mut config = cmake::Config::new(".");
.uses_cxx11() config.uses_cxx11()
.generator("Ninja") .generator("Ninja")
.profile(match is_debug { .profile(match is_debug {
true => "Debug", true => "Debug",
@ -53,9 +53,16 @@ fn build_backend(is_debug: bool, opt_level: &str, out_dir: &PathBuf) -> (PathBuf
.env("OPT_LEVEL", opt_level) .env("OPT_LEVEL", opt_level)
.define("CMAKE_INSTALL_PREFIX", &install_path) .define("CMAKE_INSTALL_PREFIX", &install_path)
.define("CMAKE_CUDA_COMPILER", "/usr/local/cuda/bin/nvcc") .define("CMAKE_CUDA_COMPILER", "/usr/local/cuda/bin/nvcc")
.define("Python3_ROOT_DIR", "../venv")
.define("TGI_TRTLLM_BACKEND_TARGET_CUDA_ARCH_LIST", cuda_arch_list) .define("TGI_TRTLLM_BACKEND_TARGET_CUDA_ARCH_LIST", cuda_arch_list)
.define("TGI_TRTLLM_BACKEND_TRT_ROOT", tensorrt_path) .define("TGI_TRTLLM_BACKEND_TRT_ROOT", tensorrt_path);
.build();
// Allow to override which Python to use ...
if let Some(python3) = option_env!("Python3_EXECUTABLE") {
config.define("Python3_EXECUTABLE", python3);
}
config.build();
// Additional transitive CMake dependencies // Additional transitive CMake dependencies
let deps_folder = out_dir.join("build").join("_deps"); let deps_folder = out_dir.join("build").join("_deps");

6
backends/trtllm/cmake/trtllm.cmake
View File

@ -21,11 +21,13 @@ else ()
set(NVTX_DISABLE ON) set(NVTX_DISABLE ON)
endif () endif ()
find_package(Python3 REQUIRED Interpreter)
fetchcontent_declare( fetchcontent_declare(
trtllm trtllm
GIT_REPOSITORY https://github.com/NVIDIA/TensorRT-LLM.git GIT_REPOSITORY https://github.com/NVIDIA/TensorRT-LLM.git
GIT_TAG c994b697313b8d36527ba346a0c5e8e374616c95 GIT_TAG 385626572df16175dd327fa785e4434cb7866a64
GIT_SHALLOW ON GIT_SHALLOW OFF
DOWNLOAD_EXTRACT_TIMESTAMP DOWNLOAD_EXTRACT_TIMESTAMP
) )
fetchcontent_makeavailable(trtllm) fetchcontent_makeavailable(trtllm)