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(backend): lets try...

Browse Source
This commit is contained in:
Morgan Funtowicz 2024-12-18 17:12:25 +01:00
parent 37aa2c6470
commit 39b4239760
2 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Dockerfile_trtllm
View File

@ -16,8 +16,11 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
g++-14 \
git \
git-lfs \
lld \
libssl-dev \
libucx-dev \
libasan8 \
libubsan1 \
ninja-build \
pkg-config \
pipx \
@ -79,12 +82,13 @@ ENV CMAKE_PREFIX_PATH="/usr/local/mpi:/usr/local/tensorrt:$CMAKE_PREFIX_PATH"
ENV CUDA_ARCH_LIST=${cuda_arch_list}
ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH"
ENV PKG_CONFIG_PATH="/usr/local/mpi/lib/pkgconfig:$PKG_CONFIG_PATH"
ENV USE_LLD_LINKER=ON
COPY . .
COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi
RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \
python3 scripts/setup_sccache.py --is-gha-build ${is_gha_build} -k ${aws_access_key_id} -s ${aws_secret_key_id} -t ${aws_session_token} -b ${sccache_bucket} -r ${sscache_region} -p ${sccache_s3_key_prefix }&& \
python3 scripts/setup_sccache.py --is-gha-build ${is_gha_build} -k ${aws_access_key_id} -s ${aws_secret_key_id} -t ${aws_session_token} -b ${sccache_bucket} -r ${sscache_region} -p ${sccache_s3_key_prefix } && \
RUSTC_WRAPPER=sccache CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --profile ${build_type} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm
FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS runtime

9
backends/trtllm/CMakeLists.txt
View File

@ -80,7 +80,8 @@ target_link_libraries(tgi_trtllm_backend_impl PUBLIC nlohmann_json::nlohmann_jso
target_link_libraries(tgi_trtllm_backend_impl PRIVATE tensorrt_llm nvinfer_plugin_tensorrt_llm tensorrt_llm_nvrtc_wrapper)
# This install all the artifacts in CMAKE_INSTALL_PREFIX under include/ lib/ bin/ to make easy to link / find it back
install(TARGETS tgi_trtllm_backend_impl tensorrt_llm nvinfer_plugin_tensorrt_llm decoder_attention executorWorker)
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)
if (NOT ${TGI_TRTLLM_BACKEND_DEBUG})
install(FILES ${TRTLLM_EXECUTOR_STATIC_LIBRARY_PATH} TYPE LIB)
@ -108,9 +109,9 @@ if (${TGI_TRTLLM_BACKEND_BUILD_TESTS})
target_link_libraries(tgi_trtllm_backend_tests PRIVATE tensorrt_llm nvinfer_plugin_tensorrt_llm tensorrt_llm_nvrtc_wrapper)
if (CMAKE_BUILD_TYPE MATCHES "Debug")
# set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fsanitize=address -fsanitize=undefined")
# set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=address -fsanitize=undefined")
# target_link_options(tgi_trtllm_backend_tests BEFORE PUBLIC -fsanitize=undefined PUBLIC -fsanitize=address)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fsanitize=address -fsanitize=undefined")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=address -fsanitize=undefined")
target_link_options(tgi_trtllm_backend_tests BEFORE PUBLIC -fsanitize=undefined PUBLIC -fsanitize=address)
endif ()
if(CMAKE_BUILD_TYPE MATCHES "Debug")