Mnist works at the moment with trt8,others like yolo4tiny and mobilenet generate the engine files but crash after throwing nvifer1::CudaRuntimeError and when demo is being run ,it doesnt deserialize properly and crashes
This commit is contained in:
+2
-1
@@ -33,12 +33,13 @@ SET(CUDA_SEPARABLE_COMPILATION ON)
|
||||
#set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -arch=sm_30 --compiler-options '-fPIC'")
|
||||
set(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS} --maxrregcount=32)
|
||||
|
||||
|
||||
find_package(CUDNN REQUIRED)
|
||||
include_directories(${CUDNN_INCLUDE_DIR})
|
||||
|
||||
|
||||
# compile
|
||||
file(GLOB tkdnn_CUSRC "src/kernels/*.cu" "src/sorting.cu")
|
||||
file(GLOB tkdnn_CUSRC "src/kernels/*.cu" "src/sorting.cu" )
|
||||
cuda_include_directories(${CMAKE_CURRENT_SOURCE_DIR}/include ${CUDA_INCLUDE_DIRS} ${CUDNN_INCLUDE_DIRS})
|
||||
cuda_add_library(kernels SHARED ${tkdnn_CUSRC})
|
||||
target_link_libraries(kernels ${CUDA_CUBLAS_LIBRARIES})
|
||||
|
||||
Reference in New Issue
Block a user