FasterTransformer: fastertransformer/kernels/add_bias_transpose_kernels.cu(161): error: identifier "uint32_t" is undefined detected during instantiation of "void fastertransformer::invokeTransposeMultiHeadToSingle(T *, T *, int, int, int, int, cudaStream_t) [with T=half]" (215): here
Description
fastertransformer/kernels/add_bias_transpose_kernels.cu(161): error: identifier "uint32_t" is undefined
detected during instantiation of "void fastertransformer::invokeTransposeMultiHeadToSingle(T *, T *, int, int, int, int, cudaStream_t) [with T=half]"
(215): here
Reproduced Steps
cmake -DSM=xx -DCMAKE_BUILD_TYPE=Release -DBUILD_PYT=ON -DBUILD_MULTI_GPU=ON ..
make -j8
About this issue
- Original URL
- State: closed
- Created 2 years ago
- Comments: 22
I ended up sticking an
export CUDAFLAGS="-include stdio.h"
in front of thecmake
call.