huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-06-19 15:52:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

move to TensorRT-LLM v0.11.0

Browse Source
This commit is contained in:
Morgan Funtowicz 2024-07-23 07:35:00 +00:00
parent ff151b738b
commit d9decb4c2c
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
backends/trtllm/cmake/trtllm.cmake
View File

@ -2,7 +2,6 @@ set(TRT_INCLUDE_DIR ${TGI_TRTLLM_BACKEND_TRT_INCLUDE_DIR})
set(TRT_LIB_DIR ${TGI_TRTLLM_BACKEND_TRT_LIB_DIR}) set(TRT_LIB_DIR ${TGI_TRTLLM_BACKEND_TRT_LIB_DIR})
set(USE_CXX11_ABI ON) set(USE_CXX11_ABI ON)
set(NVTX_DISABLE OFF)
set(BUILD_PYT OFF) set(BUILD_PYT OFF)
set(BUILD_PYBIND OFF) set(BUILD_PYBIND OFF)
set(BUILD_MICRO_BENCHMARKS OFF) set(BUILD_MICRO_BENCHMARKS OFF)
@ -14,15 +13,17 @@ message(STATUS "Building for CUDA Architectures: ${CMAKE_CUDA_ARCHITECTURES}")
if (${CMAKE_BUILD_TYPE} STREQUAL "Debug") if (${CMAKE_BUILD_TYPE} STREQUAL "Debug")
set(FAST_BUILD ON) set(FAST_BUILD ON)
set(NVTX_DISABLE OFF)
else () else ()
set(FAST_BUILD OFF) set(FAST_BUILD OFF)
set(FAST_MATH ON) set(FAST_MATH ON)
set(NVTX_DISABLE ON)
endif () endif ()
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 9691e12bce7ae1c126c435a049eb516eb119486c GIT_TAG 05316d3313360012536ace46c781518f5afae75e
GIT_SHALLOW FALSE GIT_SHALLOW FALSE
) )
fetchcontent_makeavailable(trtllm) fetchcontent_makeavailable(trtllm)