mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-24 16:32:12 +00:00
17367438f3
* test(ctest) enable address sanitizer * feat(trtllm): expose finish reason to Rust * feat(trtllm): fix logits retrieval * misc(ci): enabe building tensorrt-llm * misc(ci): update Rust action toolchain * misc(ci): let's try to build the Dockerfile for trtllm # Conflicts: # Dockerfile_trtllm * misc(ci): provide mecanism to cache inside container * misc(ci): export aws creds as output of step * misc(ci): let's try this way * misc(ci): again * misc(ci): again * misc(ci): add debug profile * misc(ci): add debug profile * misc(ci): lets actually use sccache ... * misc(ci): do not build with ssl enabled * misc(ci): WAT * misc(ci): WAT * misc(ci): WAT * misc(ci): WAT * misc(ci): WAT * misc(backend): test with TGI S3 conf * misc(backend): test with TGI S3 conf * misc(backend): once more? * misc(backend): let's try with GHA * misc(backend): missing env directive * misc(backend): make sure to correctly set IS_GHA_BUILD=true in wf * misc(backend): ok let's debug smtg * misc(backend): WWWWWWWWWWWWWAAAAAAAA * misc(backend): kthxbye retry s3 * misc(backend): use session token * misc(backend): add more info * misc(backend): lets try 1h30 * misc(backend): lets try 1h30 * misc(backend): increase to 2h * misc(backend): lets try... * misc(backend): lets try... * misc(backend): let's build for ci-runtime * misc(backend): let's add some more tooling * misc(backend): add some tags * misc(backend): disable Werror for now * misc(backend): added automatic gha detection * misc(backend): remove leak sanitizer which is included in asan * misc(backend): forward env * misc(backend): forward env * misc(backend): let's try * misc(backend): let's try * misc(backend): again * misc(backend): again * misc(backend): again * misc(backend): again * misc(backend): again * misc(backend): fix sscache -> sccache * misc(backend): fix sscache -> sccache * misc(backend): fix sscache -> sccache * misc(backend): let's actually cache things now * misc(backend): let's actually cache things now * misc(backend): attempt to run the testS? * misc(backend): attempt to run the tests? * misc(backend): attempt to run the tests? * change runner size * fix: Correctly tag docker images (#2878) * fix: Correctly tag docker images * fix: Correctly tag docker images * misc(llamacpp): maybe? * misc(llamacpp): maybe? * misc(llamacpp): maybe? * misc(ci): gogogo * misc(ci): gogogo * misc(ci): gogogo * misc(ci): gogogo * misc(ci): gogogo * misc(ci): gogogo * misc(ci): go * misc(ci): go * misc(ci): go * misc(ci): use bin folder * misc(ci): make the wf callable for reuse * misc(ci): make the wf callable for reuse (bis) * misc(ci): make the wf callable for reuse (bis) * misc(ci): give the wf a name * Create test-trtllm.yml * Update test-trtllm.yml * Create build-trtllm2 * Rename build-trtllm2 to 1-build-trtllm2 * Rename test-trtllm.yml to 1-test-trtllm2.yml * misc(ci): fw secrets * Update 1-test-trtllm2.yml * Rename 1-build-trtllm2 to 1-build-trtllm2.yml * Update 1-test-trtllm2.yml * misc(ci): use ci-build.yaml as main dispatcher * Delete .github/workflows/1-test-trtllm2.yml * Delete .github/workflows/1-build-trtllm2.yml * misc(ci): rights? * misc(ci): rights? * misc(ci): once more? * misc(ci): once more? * misc(ci): baby more time? * misc(ci): baby more time? * misc(ci): try the permission above again? * misc(ci): try the permission above again? * misc(ci): try the permission scoped again? * misc(ci): install tensorrt_llm_executor_static * misc(ci): attempt to rebuild with sccache? * misc(ci):run the tests on GPU instance * misc(ci): let's actually setup sccache in the build.rs * misc(ci): reintroduce variables * misc(ci): enforce sccache * misc(ci): correct right job name dependency * misc(ci): detect dev profile for debug * misc(ci): detect gha build * misc(ci): detect gha build * misc(ci): ok debug * misc(ci): wtf * misc(ci): wtf2 * misc(ci): wtf3 * misc(ci): use commit HEAD instead of merge commit for image id * misc(ci): wtfinfini * misc(ci): wtfinfini * misc(ci): KAMEHAMEHA * Merge TRTLLM in standard CI * misc(ci): remove input machine * misc(ci): missing id-token for AWS auth * misc(ci): missing id-token for AWS auth * misc(ci): missing id-token for AWS auth * misc(ci): again... * misc(ci): again... * misc(ci): again... * misc(ci): again... * misc(ci): missing benchmark * misc(ci): missing backends * misc(ci): missing launcher * misc(ci): give everything aws needs * misc(ci): give everything aws needs * misc(ci): fix warnings * misc(ci): attempt to fix sccache not building trtllm * misc(ci): attempt to fix sccache not building trtllm again --------- Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com> Co-authored-by: Hugo Larcher <hugo.larcher@huggingface.co> Co-authored-by: Pauline Bailly-Masson <155966238+paulinebm@users.noreply.github.com>
49 lines
2.1 KiB
CMake
49 lines
2.1 KiB
CMake
set(TRT_INCLUDE_DIR ${TGI_TRTLLM_BACKEND_TRT_INCLUDE_DIR})
|
|
set(TRT_LIB_DIR ${TGI_TRTLLM_BACKEND_TRT_LIB_DIR})
|
|
|
|
set(USE_CXX11_ABI ON)
|
|
set(BUILD_PYT OFF)
|
|
set(BUILD_PYBIND OFF)
|
|
set(BUILD_MICRO_BENCHMARKS OFF)
|
|
set(BUILD_BENCHMARKS OFF)
|
|
set(BUILD_TESTS OFF)
|
|
set(CMAKE_CUDA_ARCHITECTURES ${TGI_TRTLLM_BACKEND_TARGET_CUDA_ARCH_LIST})
|
|
|
|
message(STATUS "Building for CUDA Architectures: ${CMAKE_CUDA_ARCHITECTURES}")
|
|
|
|
set(ENABLE_UCX OFF)
|
|
if (${CMAKE_BUILD_TYPE} STREQUAL "Debug")
|
|
set(FAST_BUILD ON)
|
|
set(NVTX_DISABLE ON)
|
|
set(INDEX_RANGE_CHECK ON)
|
|
else ()
|
|
set(FAST_BUILD OFF)
|
|
set(FAST_MATH ON)
|
|
set(NVTX_DISABLE OFF)
|
|
set(INDEX_RANGE_CHECK OFF)
|
|
endif ()
|
|
|
|
find_package(Python3 REQUIRED Interpreter)
|
|
|
|
fetchcontent_declare(
|
|
trtllm
|
|
GIT_REPOSITORY https://github.com/huggingface/TensorRT-LLM.git
|
|
GIT_TAG 1bb9ca4688805444f203647674bac1d7219d0579
|
|
GIT_SHALLOW ON
|
|
DOWNLOAD_EXTRACT_TIMESTAMP
|
|
)
|
|
fetchcontent_makeavailable(trtllm)
|
|
|
|
message(STATUS "Found TensorRT-LLM: ${trtllm_SOURCE_DIR}")
|
|
execute_process(COMMAND git lfs install WORKING_DIRECTORY "${trtllm_SOURCE_DIR}/")
|
|
execute_process(COMMAND git lfs pull WORKING_DIRECTORY "${trtllm_SOURCE_DIR}/")
|
|
|
|
# TRTLLM use a JIT based *precompiled* library to generate some specific kernels, we are generating the path to this one here
|
|
set(TRTLLM_NVRTC_LIBRARY_NAME "${CMAKE_SHARED_LIBRARY_PREFIX}tensorrt_llm_nvrtc_wrapper${CMAKE_SHARED_LIBRARY_SUFFIX}" CACHE INTERNAL "nvrtc wrapper library name")
|
|
set(TRTLLM_NVRTC_WRAPPER_LIBRARY_PATH "${trtllm_SOURCE_DIR}/cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/decoderXQAImplJIT/nvrtcWrapper/${CMAKE_LIBRARY_ARCHITECTURE}/${TRTLLM_NVRTC_LIBRARY_NAME}"
|
|
CACHE INTERNAL "nvrtc wrapper library path")
|
|
|
|
# The same Executor Static library
|
|
set(TRTLLM_EXECUTOR_STATIC_LIBRARY_NAME "${CMAKE_SHARED_LIBRARY_PREFIX}tensorrt_llm_executor_static${CMAKE_STATIC_LIBRARY_SUFFIX}" CACHE INTERNAL "executor_static library name")
|
|
set(TRTLLM_EXECUTOR_STATIC_LIBRARY_PATH "${trtllm_SOURCE_DIR}/cpp/tensorrt_llm/executor/${CMAKE_LIBRARY_ARCHITECTURE}/${TRTLLM_EXECUTOR_STATIC_LIBRARY_NAME}" CACHE INTERNAL "executor_static library path")
|