diff --git a/Dockerfile_trtllm b/Dockerfile_trtllm index cbe4b3d3..b30c0fa3 100644 --- a/Dockerfile_trtllm +++ b/Dockerfile_trtllm @@ -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 diff --git a/backends/trtllm/CMakeLists.txt b/backends/trtllm/CMakeLists.txt index 26af80be..7cd6e85a 100644 --- a/backends/trtllm/CMakeLists.txt +++ b/backends/trtllm/CMakeLists.txt @@ -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)