huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-21 23:12:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(backend): enable compiler warning if support for RVO not applying

Browse Source
This commit is contained in:
Morgan Funtowicz 2024-11-30 23:16:35 +01:00
parent 9bb6309712
commit 87272ffe39
2 changed files with 7 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
backends/trtllm/CMakeLists.txt
View File

@ -17,6 +17,7 @@ set(CMAKE_CXX_STANDARD 23)
include(FetchContent) include(FetchContent)
include(ExternalProject) include(ExternalProject)
include(CheckCXXCompilerFlag)
option(TGI_TRTLLM_BACKEND_BUILD_TESTS "Enable building the unittests suite" OFF) option(TGI_TRTLLM_BACKEND_BUILD_TESTS "Enable building the unittests suite" OFF)
option(TGI_TRTLLM_BACKEND_BUILD_EXAMPLES "Enable building the examples suite" OFF) option(TGI_TRTLLM_BACKEND_BUILD_EXAMPLES "Enable building the examples suite" OFF)
@ -33,6 +34,12 @@ include(cmake/json.cmake)
include(cmake/spdlog.cmake) include(cmake/spdlog.cmake)
include(cmake/trtllm.cmake) include(cmake/trtllm.cmake)
# This attempt to detect if the compiler can emit warning if it can't apply return value optimization from a function
check_cxx_compiler_flag("-Wnrvo" COMPILER_SUPPORT_WARNING_ON_NVRO)
if(${COMPILER_SUPPORT_WARNING_ON_NVRO})
set(CMAKE_CXX_FLAGS "{CMAKE_CXX_FLAGS} -Wnvro")
endif()
# Let's build TRTLLM as part of CMake # Let's build TRTLLM as part of CMake
add_subdirectory("${trtllm_SOURCE_DIR}/cpp" "${trtllm_SOURCE_DIR}/..") add_subdirectory("${trtllm_SOURCE_DIR}/cpp" "${trtllm_SOURCE_DIR}/..")

14
backends/trtllm/tests/infer_test.cpp
View File

@ -1,14 +0,0 @@
//
// Created by mfuntowicz on 7/2/24.
//
#include <catch2/catch_all.hpp>
#include <spdlog/spdlog.h>
#include "../include/backend.h"
TEST_CASE("Load TRTLLM Engine on the TGI Backend", "[trtllm][engine][load]") {
const auto engines = std::filesystem::path("/home/mfuntowicz/.cache/huggingface/assets/trtllm/0.11.0.dev2024062500/meta-llama--Meta-Llama-3-8B-Instruct/4090/engines/");
const auto executor = std::filesystem::path("/home/mfuntowicz/Workspace/text-generation-inference/backends/trtllm/cmake-build-debug/cmake-build-debug/_deps/trtllm-src/cpp/tensorrt_llm/executor_worker/executorWorker");
spdlog::info("Loading config from: {}", absolute(engines).string());
huggingface::tgi::backends::TensorRtLlmBackend backend(engines, executor);
}