API tools faq
paste
Advertisement
damian101

tensorrt AUR build

damian101
Aug 27th, 2023
2,152
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Make 85.41 KB | None | 0 0
raw download clone embed print report
  1. [ 79%] Building CUDA object plugin/CMakeFiles/nvinfer_plugin.dir/embLayerNormPlugin/embLayerNormKernel.cu.o
  2. /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu(228): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  3.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  4.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  5.               threadData = pairSum(threadData, kvp<T>(rldval, rldval * val));
  6.                            ^
  7.           detected during:
  8.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247
  9.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253
  10.  
  11. /opt/cuda/include/cub/block/specializations/../../warp/specializations/warp_reduce_shfl.cuh(360): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  12.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  13.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  14.               output = reduction_op(input, temp);
  15.                        ^
  16.           detected during:
  17.             instantiation of "_T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::WarpReduceShfl<T, LOGICAL_WARP_THREADS, LEGACY_PTX_ARCH>::ReduceStep(_T, ReductionOp, int, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, LOGICAL_WARP_THREADS=32, LEGACY_PTX_ARCH=0, _T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 388
  18.             instantiation of "_T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::WarpReduceShfl<T, LOGICAL_WARP_THREADS, LEGACY_PTX_ARCH>::ReduceStep(_T, ReductionOp, int, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<0>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, LOGICAL_WARP_THREADS=32, LEGACY_PTX_ARCH=0, _T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 403
  19.             instantiation of "void cub::CUB_200101_700_720_750_800_860_870_890_900_NS::WarpReduceShfl<T, LOGICAL_WARP_THREADS, LEGACY_PTX_ARCH>::ReduceStep(T &, ReductionOp, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<STEP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, LOGICAL_WARP_THREADS=32, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, STEP=0]" at line 449
  20.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::WarpReduceShfl<T, LOGICAL_WARP_THREADS, LEGACY_PTX_ARCH>::ReduceImpl(cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<1>, T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, LOGICAL_WARP_THREADS=32, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 530
  21.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::WarpReduceShfl<T, LOGICAL_WARP_THREADS, LEGACY_PTX_ARCH>::Reduce<ALL_LANES_VALID,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, LOGICAL_WARP_THREADS=32, LEGACY_PTX_ARCH=0, ALL_LANES_VALID=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 204 of /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh
  22.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  23.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  24.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  25.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  26.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  27.  
  28. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  29.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  30.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  31.               warp_aggregate = reduction_op(warp_aggregate, addend);
  32.                                ^
  33.           detected during:
  34.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=1]" at line 156
  35.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp>(ReductionOp, T, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 207
  36.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  37.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  38.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  39.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  40.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  41.  
  42. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  43.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  44.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  45.               warp_aggregate = reduction_op(warp_aggregate, addend);
  46.                                ^
  47.           detected during:
  48.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=2]" at line 121
  49.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=1]" at line 156
  50.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp>(ReductionOp, T, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 207
  51.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  52.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  53.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  54.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  55.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  56.  
  57. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  58.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  59.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  60.               warp_aggregate = reduction_op(warp_aggregate, addend);
  61.                                ^
  62.           detected during:
  63.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=3]" at line 121
  64.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=2]" at line 121
  65.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=1]" at line 156
  66.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp>(ReductionOp, T, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 207
  67.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  68.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  69.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  70.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  71.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  72.  
  73. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  74.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  75.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  76.               warp_aggregate = reduction_op(warp_aggregate, addend);
  77.                                ^
  78.           detected during:
  79.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=4]" at line 121
  80.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=3]" at line 121
  81.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=2]" at line 121
  82.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=1]" at line 156
  83.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp>(ReductionOp, T, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 207
  84.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  85.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  86.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  87.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  88.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  89.  
  90. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  91.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  92.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  93.               warp_aggregate = reduction_op(warp_aggregate, addend);
  94.                                ^
  95.           detected during:
  96.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=5]" at line 121
  97.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=4]" at line 121
  98.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=3]" at line 121
  99.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=2]" at line 121
  100.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=1]" at line 156
  101.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp>(ReductionOp, T, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 207
  102.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  103.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  104.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  105.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  106.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  107.  
  108. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  109.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  110.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  111.               warp_aggregate = reduction_op(warp_aggregate, addend);
  112.                                ^
  113.           detected during:
  114.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=6]" at line 121
  115.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=5]" at line 121
  116.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=4]" at line 121
  117.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=3]" at line 121
  118.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=2]" at line 121
  119.             [ 2 instantiation contexts not shown ]
  120.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  121.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  122.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  123.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  124.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  125.  
  126. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  127.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  128.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  129.               warp_aggregate = reduction_op(warp_aggregate, addend);
  130.                                ^
  131.           detected during:
  132.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=7]" at line 121
  133.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=6]" at line 121
  134.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=5]" at line 121
  135.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=4]" at line 121
  136.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=3]" at line 121
  137.             [ 3 instantiation contexts not shown ]
  138.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  139.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  140.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  141.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  142.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  143.  
  144. 9 errors detected in the compilation of "/home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu".
  145. make[2]: *** [plugin/CMakeFiles/nvinfer_plugin.dir/build.make:3075: plugin/CMakeFiles/nvinfer_plugin.dir/embLayerNormPlugin/embLayerNormKernel.cu.o] Error 1
  146. make[1]: *** [CMakeFiles/Makefile2:1040: plugin/CMakeFiles/nvinfer_plugin.dir/all] Error 2
  147. make[1]: *** Waiting for unfinished jobs....
  148. [ 79%] Building CUDA object plugin/CMakeFiles/nvinfer_plugin_static.dir/common/kernels/rproiInferenceFused.cu.o
  149. [ 79%] Building CUDA object plugin/CMakeFiles/nvinfer_plugin_static.dir/common/kernels/sortScoresPerClass.cu.o
  150. [ 80%] Building CUDA object plugin/CMakeFiles/nvinfer_plugin_static.dir/common/kernels/sortScoresPerImage.cu.o
  151. [ 80%] Building CUDA object plugin/CMakeFiles/nvinfer_plugin_static.dir/common/kernels/voxelGeneratorKernels.cu.o
  152. [ 80%] Building CUDA object plugin/CMakeFiles/nvinfer_plugin_static.dir/bertQKVToContextPlugin/qkvToContext.cu.o
  153. [ 80%] Building CUDA object plugin/CMakeFiles/nvinfer_plugin_static.dir/bertQKVToContextPlugin/zeroPadding2d.cu.o
  154. [ 80%] Building CUDA object plugin/CMakeFiles/nvinfer_plugin_static.dir/embLayerNormPlugin/embLayerNormKernel.cu.o
  155. /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu(228): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  156.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  157.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  158.               threadData = pairSum(threadData, kvp<T>(rldval, rldval * val));
  159.                            ^
  160.           detected during:
  161.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247
  162.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253
  163.  
  164. /opt/cuda/include/cub/block/specializations/../../warp/specializations/warp_reduce_shfl.cuh(360): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  165.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  166.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  167.               output = reduction_op(input, temp);
  168.                        ^
  169.           detected during:
  170.             instantiation of "_T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::WarpReduceShfl<T, LOGICAL_WARP_THREADS, LEGACY_PTX_ARCH>::ReduceStep(_T, ReductionOp, int, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, LOGICAL_WARP_THREADS=32, LEGACY_PTX_ARCH=0, _T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 388
  171.             instantiation of "_T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::WarpReduceShfl<T, LOGICAL_WARP_THREADS, LEGACY_PTX_ARCH>::ReduceStep(_T, ReductionOp, int, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<0>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, LOGICAL_WARP_THREADS=32, LEGACY_PTX_ARCH=0, _T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 403
  172.             instantiation of "void cub::CUB_200101_700_720_750_800_860_870_890_900_NS::WarpReduceShfl<T, LOGICAL_WARP_THREADS, LEGACY_PTX_ARCH>::ReduceStep(T &, ReductionOp, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<STEP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, LOGICAL_WARP_THREADS=32, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, STEP=0]" at line 449
  173.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::WarpReduceShfl<T, LOGICAL_WARP_THREADS, LEGACY_PTX_ARCH>::ReduceImpl(cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<1>, T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, LOGICAL_WARP_THREADS=32, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 530
  174.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::WarpReduceShfl<T, LOGICAL_WARP_THREADS, LEGACY_PTX_ARCH>::Reduce<ALL_LANES_VALID,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, LOGICAL_WARP_THREADS=32, LEGACY_PTX_ARCH=0, ALL_LANES_VALID=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 204 of /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh
  175.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  176.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  177.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  178.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  179.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  180.  
  181. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  182.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  183.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  184.               warp_aggregate = reduction_op(warp_aggregate, addend);
  185.                                ^
  186.           detected during:
  187.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=1]" at line 156
  188.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp>(ReductionOp, T, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 207
  189.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  190.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  191.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  192.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  193.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  194.  
  195. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  196.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  197.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  198.               warp_aggregate = reduction_op(warp_aggregate, addend);
  199.                                ^
  200.           detected during:
  201.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=2]" at line 121
  202.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=1]" at line 156
  203.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp>(ReductionOp, T, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 207
  204.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  205.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  206.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  207.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  208.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  209.  
  210. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  211.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  212.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  213.               warp_aggregate = reduction_op(warp_aggregate, addend);
  214.                                ^
  215.           detected during:
  216.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=3]" at line 121
  217.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=2]" at line 121
  218.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=1]" at line 156
  219.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp>(ReductionOp, T, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 207
  220.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  221.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  222.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  223.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  224.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  225.  
  226. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  227.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  228.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  229.               warp_aggregate = reduction_op(warp_aggregate, addend);
  230.                                ^
  231.           detected during:
  232.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=4]" at line 121
  233.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=3]" at line 121
  234.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=2]" at line 121
  235.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=1]" at line 156
  236.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp>(ReductionOp, T, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 207
  237.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  238.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  239.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  240.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  241.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  242.  
  243. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  244.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  245.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  246.               warp_aggregate = reduction_op(warp_aggregate, addend);
  247.                                ^
  248.           detected during:
  249.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=5]" at line 121
  250.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=4]" at line 121
  251.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=3]" at line 121
  252.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=2]" at line 121
  253.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=1]" at line 156
  254.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp>(ReductionOp, T, int) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 207
  255.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  256.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  257.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  258.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  259.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  260.  
  261. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  262.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  263.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  264.               warp_aggregate = reduction_op(warp_aggregate, addend);
  265.                                ^
  266.           detected during:
  267.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=6]" at line 121
  268.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=5]" at line 121
  269.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=4]" at line 121
  270.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=3]" at line 121
  271.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=2]" at line 121
  272.             [ 2 instantiation contexts not shown ]
  273.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  274.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  275.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  276.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  277.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  278.  
  279. /opt/cuda/include/cub/block/specializations/block_reduce_warp_reductions.cuh(119): error: no instance of function template "cuda::std::__4::plus<void>::operator()" matches the argument list
  280.             argument types are: (cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>)
  281.             object type is: cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum
  282.               warp_aggregate = reduction_op(warp_aggregate, addend);
  283.                                ^
  284.           detected during:
  285.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=7]" at line 121
  286.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=6]" at line 121
  287.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=5]" at line 121
  288.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=4]" at line 121
  289.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::ApplyWarpAggregates<FULL_TILE,ReductionOp,SUCCESSOR_WARP>(ReductionOp, T, int, cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Int2Type<SUCCESSOR_WARP>) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum, SUCCESSOR_WARP=3]" at line 121
  290.             [ 3 instantiation contexts not shown ]
  291.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduceWarpReductions<T, BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce<FULL_TILE,ReductionOp>(T, int, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, FULL_TILE=true, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 354 of /opt/cuda/include/cub/block/block_reduce.cuh
  292.             instantiation of "T cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BlockReduce<T, BLOCK_DIM_X, ALGORITHM, BLOCK_DIM_Y, BLOCK_DIM_Z, LEGACY_PTX_ARCH>::Reduce(T, ReductionOp) [with T=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::KeyValuePair<float, float>, BLOCK_DIM_X=256, ALGORITHM=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::BLOCK_REDUCE_WARP_REDUCTIONS, BLOCK_DIM_Y=1, BLOCK_DIM_Z=1, LEGACY_PTX_ARCH=0, ReductionOp=cub::CUB_200101_700_720_750_800_860_870_890_900_NS::Sum]" at line 257 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/common/common.cuh
  293.             instantiation of "void layerNorm<T,R,P,TPB>(const kvp<R> &, int32_t, int32_t, const P *, const P *, T *) [with T=float, R=float, P=float, TPB=256]" at line 233 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  294.             instantiation of "void nvinfer1::plugin::bert::embLayerNormKernel<T,TPB>(int, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float, TPB=256U]" at line 247 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  295.             instantiation of "int32_t nvinfer1::plugin::bert::embSkipLayerNorm(cudaStream_t, int32_t, int32_t, int32_t, const int32_t *, const int32_t *, const float *, const float *, const T *, const T *, const T *, int32_t, int32_t, T *) [with T=float]" at line 253 of /home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu
  296.  
  297. 9 errors detected in the compilation of "/home/damian101/.cache/yay/tensorrt/src/TensorRT/plugin/embLayerNormPlugin/embLayerNormKernel.cu".
  298. make[2]: *** [plugin/CMakeFiles/nvinfer_plugin_static.dir/build.make:3075: plugin/CMakeFiles/nvinfer_plugin_static.dir/embLayerNormPlugin/embLayerNormKernel.cu.o] Error 1
  299. make[2]: *** Waiting for unfinished jobs....
  300. make[1]: *** [CMakeFiles/Makefile2:1066: plugin/CMakeFiles/nvinfer_plugin_static.dir/all] Error 2
  301. make: *** [Makefile:156: all] Error 2
  302. ==> ERROR: A failure occurred in build().
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!