huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

backend(trtllm): use correct library reference decoder_attention_src

Browse Source
This commit is contained in:
Morgan Funtowicz 2025-02-05 15:33:36 +01:00
parent 9f6f1e905d
commit 11c9acab42
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Dockerfile_trtllm
View File

@ -1,4 +1,4 @@
ARG cuda_arch_list="75-real;80-real;86-real;89-real;90-real;100-real"
ARG cuda_arch_list="75-real;80-real;86-real;89-real;90-real;100-real;120-real"
ARG cuda_base=12.8.0
ARG build_type=release
ARG ompi_version=4.1.7

2
backends/trtllm/CMakeLists.txt
View File

@ -59,7 +59,7 @@ target_link_libraries(tgi_trtllm_backend_impl PRIVATE tensorrt_llm nvinfer_plugi
# 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)
install(TARGETS tensorrt_llm nvinfer_plugin_tensorrt_llm decoder_attention executorWorker)
install(TARGETS tensorrt_llm nvinfer_plugin_tensorrt_llm decoder_attention_src 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)