optimization/kernel_evidence.json

{
  "fp8_sm120_launches": 224,
  "native_bf16_flash_attention": 32,
  "all_kernels": {
    "void cutlass::Kernel2<cutlass_80_tensorop_bf16_s16816gemm_relu_bf16_128x256_32x3_tt_align8>(cutlass_80_tensorop_bf16_s16816gemm_relu_bf16_128x256_32x3_tt_align8::Params)": 1,
    "void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#7}::operator()() const::{lambda(float)#1}, std::array<char*, 2ul>, 4, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1> >(int, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#7}::operator()() const::{lambda(float)#1}, std::array<char*, 2ul>, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1>)": 3,
    "void at::native::vectorized_elementwise_kernel<4, at::native::(anonymous namespace)::pow_tensor_scalar_kernel_impl<float, float>(at::TensorIteratorBase&, float)::{lambda(float)#1}, std::array<char*, 2ul>, false>(int, at::native::(anonymous namespace)::pow_tensor_scalar_kernel_impl<float, float>(at::TensorIteratorBase&, float)::{lambda(float)#1}, std::array<char*, 2ul>)": 1,
    "void at::native::reduce_kernel<512, 1, at::native::ReduceOp<float, at::native::MeanOps<float, float, float, float>, unsigned int, float, 4, 4> >(at::native::ReduceOp<float, at::native::MeanOps<float, float, float, float>, unsigned int, float, 4, 4>)": 1,
    "void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul>, false>(int, at::native::CUDAFunctorOnSelf_add<float>, std::array<char*, 2ul>)": 2,
    "void at::native::vectorized_elementwise_kernel<4, at::native::rsqrt_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}, std::array<char*, 2ul>, false>(int, at::native::rsqrt_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}, std::array<char*, 2ul>)": 1,
    "void at::native::elementwise_kernel<128, 2, at::native::gpu_kernel_impl_nocast<at::native::BinaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> > >(at::TensorIteratorBase&, at::native::BinaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> > const&)::{lambda(int)#1}>(int, at::native::gpu_kernel_impl_nocast<at::native::BinaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> > >(at::TensorIteratorBase&, at::native::BinaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> > const&)::{lambda(int)#1})": 3,
    "void at::native::vectorized_elementwise_kernel<4, at::native::bfloat16_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda(float)#1}, std::array<char*, 2ul>, false>(int, at::native::bfloat16_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda(float)#1}, std::array<char*, 2ul>)": 2,
    "void cutlass::Kernel2<cutlass_80_tensorop_bf16_s16816gemm_relu_bf16_128x64_32x6_tn_align8>(cutlass_80_tensorop_bf16_s16816gemm_relu_bf16_128x64_32x6_tn_align8::Params)": 2,
    "void cublasLt::splitKreduce_kernel<32, 16, int, __nv_bfloat16, __nv_bfloat16, float, __nv_bfloat16, false, __nv_bfloat16, __nv_bfloat16, __nv_bfloat16, true, false, false, false>(cublasLt::cublasSplitKParams<float>, __nv_bfloat16 const*, __nv_bfloat16 const*, __nv_bfloat16*, __nv_bfloat16*, float const*, float const*, __nv_bfloat16 const*, __nv_bfloat16 const*, __nv_bfloat16*, void*, long, float*, int*, float*, float*, float const*, float const*, float const*, float const*, float const*)": 3,
    "void at::native::vectorized_elementwise_kernel<4, at::native::GeluCUDAKernelImpl(at::TensorIteratorBase&, at::native::GeluType)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(c10::BFloat16)#1}, std::array<char*, 2ul>, false>(int, at::native::GeluCUDAKernelImpl(at::TensorIteratorBase&, at::native::GeluType)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(c10::BFloat16)#1}, std::array<char*, 2ul>)": 1,
    "void at::native::vectorized_elementwise_kernel<2, at::native::FillFunctor<long>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<long>, std::array<char*, 1ul>)": 3,
    "void at::native::elementwise_kernel<128, 2, at::native::gpu_kernel_impl_nocast<at::native::(anonymous namespace)::where_kernel_impl(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(bool, unsigned long, unsigned long)#1}>(at::TensorIteratorBase&, at::native::(anonymous namespace)::where_kernel_impl(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(bool, unsigned long, unsigned long)#1} const&)::{lambda(int)#1}>(int, at::native::gpu_kernel_impl_nocast<at::native::(anonymous namespace)::where_kernel_impl(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(bool, unsigned long, unsigned long)#1}>(at::TensorIteratorBase&, at::native::(anonymous namespace)::where_kernel_impl(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(bool, unsigned long, unsigned long)#1} const&)::{lambda(int)#1})": 1,
    "void at_cuda_detail::cub::detail::scan::DeviceScanInitKernel<at_cuda_detail::cub::ScanTileState<long, true> >(at_cuda_detail::cub::ScanTileState<long, true>, int)": 3,
    "void at_cuda_detail::cub::detail::scan::DeviceScanKernel<at_cuda_detail::cub::detail::scan::policy_hub<long, long, long, unsigned int, std::plus<long> >::Policy1000, long const*, long*, at_cuda_detail::cub::ScanTileState<long, true>, std::plus<long>, at_cuda_detail::cub::NullType, unsigned int, long, false, at_cuda_detail::cub::NullType>(long const*, long*, at_cuda_detail::cub::ScanTileState<long, true>, int, std::plus<long>, at_cuda_detail::cub::NullType, unsigned int)": 3,
    "Memcpy DtoH (Device -> Pinned)": 11,
    "void at::native::vectorized_elementwise_kernel<4, at::native::compare_scalar_kernel<long>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, long)::{lambda(long)#1}, std::array<char*, 2ul>, false>(int, at::native::compare_scalar_kernel<long>(at::TensorIteratorBase&, at::native::(anonymous namespace)::OpType, long)::{lambda(long)#1}, std::array<char*, 2ul>)": 3,
    "void at::native::reduce_kernel<512, 1, at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4> >(at::native::ReduceOp<bool, at::native::func_wrapper_t<bool, at::native::and_kernel_cuda(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#12}::operator()() const::{lambda(bool, bool)#1}>, unsigned int, bool, 4, 4>)": 2,
    "void compute_cuda_kernel<long>(long const*, long const*, long*, long, long)": 3,
    "void at::native::_scatter_gather_elementwise_kernel<128, 8, at::native::_cuda_scatter_gather_internal_kernel<false, at::native::OpaqueType<1>, long>::operator()<at::native::TensorAssign>(at::TensorIterator&, long, long, long, at::native::TensorAssign const&)::{lambda(int)#1}>(int, at::native::_cuda_scatter_gather_internal_kernel<false, at::native::OpaqueType<1>, long>::operator()<at::native::TensorAssign>(at::TensorIterator&, long, long, long, at::native::TensorAssign const&)::{lambda(int)#1})": 1,
    "void at::native::vectorized_elementwise_kernel<4, at::native::FillFunctor<c10::BFloat16>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<c10::BFloat16>, std::array<char*, 1ul>)": 2,
    "void at::native::(anonymous namespace)::CatArrayBatchedCopy_vectorized<at::native::(anonymous namespace)::OpaqueType<2u>, unsigned int, 2, 128, 1, 16, 8>(char*, at::native::(anonymous namespace)::CatArrInputTensorMetadata<at::native::(anonymous namespace)::OpaqueType<2u>, unsigned int, 128, 1>, at::native::(anonymous namespace)::TensorSizeStride<unsigned int, 4u>, int, unsigned int)": 1,
    "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)": 4,
    "void at_cuda_detail::cub::detail::reduce::DeviceReduceKernel<at_cuda_detail::cub::detail::reduce::policy_hub<int, unsigned long long, cuda::std::__4::plus<void> >::Policy1000, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, unsigned long long, cuda::std::__4::plus<void>, int, cuda::std::__4::__identity>(thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, int*, unsigned long long, at_cuda_detail::cub::GridEvenShare<unsigned long long>, cuda::std::__4::plus<void>, cuda::std::__4::__identity)": 4,
    "void at_cuda_detail::cub::detail::reduce::DeviceReduceSingleTileKernel<at_cuda_detail::cub::detail::reduce::policy_hub<int, unsigned long long, cuda::std::__4::plus<void> >::Policy1000, int*, int*, int, cuda::std::__4::plus<void>, int, int, cuda::std::__4::__identity>(int*, int*, int, cuda::std::__4::plus<void>, int, cuda::std::__4::__identity)": 4,
    "void at_cuda_detail::cub::detail::scan::DeviceCompactInitKernel<at_cuda_detail::cub::ScanTileState<int, true>, int*>(at_cuda_detail::cub::ScanTileState<int, true>, int, int*)": 4,
    "void at_cuda_detail::cub::detail::select::DeviceSelectSweepKernel<at_cuda_detail::cub::detail::select::policy_hub<long, bool, int, false, (at_cuda_detail::cub::SelectImpl)0>::Policy1000, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::counting_iterator<long, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, long*, int*, at_cuda_detail::cub::ScanTileState<int, true>, at_cuda_detail::cub::NullType, at_cuda_detail::cub::NullType, int, at_cuda_detail::cub::detail::select::streaming_context_t<long, true>, (at_cuda_detail::cub::SelectImpl)0>(thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::counting_iterator<long, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::transform_iterator<at::native::(anonymous namespace)::NonZeroOp<bool>, bool const*, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default, thrust::THRUST_300001_SM_750_800_860_900_1000_1200_NS::use_default>, long*, int*, at_cuda_detail::cub::ScanTileState<int, true>, at_cuda_detail::cub::NullType, at_cuda_detail::cub::NullType, int, int, at_cuda_detail::cub::detail::select::streaming_context_t<long, true>, at_cuda_detail::cub::detail::vsmem_t)": 4,
    "void at::native::index_elementwise_kernel<128, 4, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<2> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<2> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1}>(long, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<2> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<2> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1})": 1,
    "Memcpy DtoH (Device -> Pageable)": 1,
    "Memcpy HtoD (Pageable -> Device)": 5,
    "Memcpy DtoD (Device -> Device)": 3,
    "void at::native::index_elementwise_kernel<128, 4, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<8> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<8> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1}>(long, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<8> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<8> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1})": 3,
    "void at::native::(anonymous namespace)::CatArrayBatchedCopy_vectorized<at::native::(anonymous namespace)::OpaqueType<8u>, unsigned int, 2, 128, 1, 16, 2>(char*, at::native::(anonymous namespace)::CatArrInputTensorMetadata<at::native::(anonymous namespace)::OpaqueType<8u>, unsigned int, 128, 1>, at::native::(anonymous namespace)::TensorSizeStride<unsigned int, 4u>, int, unsigned int)": 1,
    "void (anonymous namespace)::elementwise_kernel_with_index<int, at::native::arange_cuda_out(c10::Scalar const&, c10::Scalar const&, c10::Scalar const&, at::Tensor&)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1}>(int, at::native::arange_cuda_out(c10::Scalar const&, c10::Scalar const&, c10::Scalar const&, at::Tensor&)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1}, function_traits<at::native::arange_cuda_out(c10::Scalar const&, c10::Scalar const&, c10::Scalar const&, at::Tensor&)::{lambda()#1}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1}>::result_type*)": 1,
    "void at::native::_scatter_gather_elementwise_kernel<128, 8, at::native::_cuda_scatter_gather_internal_kernel<false, at::native::OpaqueType<8>, long>::operator()<at::native::TensorAssign>(at::TensorIterator&, long, long, long, at::native::TensorAssign const&)::{lambda(int)#1}>(int, at::native::_cuda_scatter_gather_internal_kernel<false, at::native::OpaqueType<8>, long>::operator()<at::native::TensorAssign>(at::TensorIterator&, long, long, long, at::native::TensorAssign const&)::{lambda(int)#1})": 1,
    "void at::native::vectorized_elementwise_kernel<4, at::native::FillFunctor<bool>, std::array<char*, 1ul>, false>(int, at::native::FillFunctor<bool>, std::array<char*, 1ul>)": 1,
    "void at::native::index_elementwise_kernel<128, 4, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<1> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<1> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1}>(long, at::native::gpu_index_kernel<at::native::index_put_kernel_impl<at::native::OpaqueType<1> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1}>(at::TensorIteratorBase&, c10::ArrayRef<long>, c10::ArrayRef<long>, at::native::index_put_kernel_impl<at::native::OpaqueType<1> >(at::TensorIterator&, c10::ArrayRef<long>, c10::ArrayRef<long>)::{lambda(char*, char const*, long)#1} const&, bool)::{lambda(int)#1})": 1,
    "void at::native::(anonymous namespace)::CatArrayBatchedCopy_alignedK_contig<at::native::(anonymous namespace)::OpaqueType<2u>, unsigned int, 1, 128, 1, 8>(at::native::(anonymous namespace)::OpaqueType<2u>*, at::native::(anonymous namespace)::CatArrInputTensorMetadata<at::native::(anonymous namespace)::OpaqueType<2u>, unsigned int, 128, 1>, at::native::(anonymous namespace)::TensorSizeStride<unsigned int, 4u>, int, unsigned int)": 1,
    "void at::native::vectorized_elementwise_kernel<4, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul>, false>(int, at::native::AUnaryFunctor<float, float, float, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 2ul>)": 1,
    "void at::native::vectorized_elementwise_kernel<4, at::native::cos_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}, std::array<char*, 2ul>, false>(int, at::native::cos_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}, std::array<char*, 2ul>)": 1,
    "void at::native::vectorized_elementwise_kernel<4, at::native::sin_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}, std::array<char*, 2ul>, false>(int, at::native::sin_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#2}::operator()() const::{lambda(float)#1}, std::array<char*, 2ul>)": 1,
    "void at::native::(anonymous namespace)::CatArrayBatchedCopy_vectorized<at::native::(anonymous namespace)::OpaqueType<4u>, unsigned int, 2, 128, 1, 16, 4>(char*, at::native::(anonymous namespace)::CatArrInputTensorMetadata<at::native::(anonymous namespace)::OpaqueType<4u>, unsigned int, 128, 1>, at::native::(anonymous namespace)::TensorSizeStride<unsigned int, 4u>, int, unsigned int)": 1,
    "void cutlass::Kernel2<cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_128x2_tn_align8>(cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_128x2_tn_align8::Params)": 1,
    "void at::native::vectorized_elementwise_kernel<4, at::native::(anonymous namespace)::silu_kernel(at::TensorIteratorBase&)::{lambda()#1}::operator()() const::{lambda()#6}::operator()() const::{lambda(c10::BFloat16)#1}, std::array<char*, 2ul>, false>(int, at::native::(anonymous namespace)::silu_kernel(at::TensorIteratorBase&)::{lambda()#1}::operator()() const::{lambda()#6}::operator()() const::{lambda(c10::BFloat16)#1}, std::array<char*, 2ul>)": 3,
    "Memset (Device)": 3,
    "void cutlass::Kernel2<cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_128x1_tn_align8>(cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_128x1_tn_align8::Params)": 2,
    "void cutlass::Kernel2<cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_64x1_tn_align8>(cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_64x1_tn_align8::Params)": 1,
    "void at::native::vectorized_elementwise_kernel<4, at::native::bitwise_not_kernel_cuda(at::TensorIteratorBase&)::{lambda(bool)#1}, std::array<char*, 2ul>, false>(int, at::native::bitwise_not_kernel_cuda(at::TensorIteratorBase&)::{lambda(bool)#1}, std::array<char*, 2ul>)": 1,
    "void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1}, std::array<char*, 2ul>, 4, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1> >(int, at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()#4}::operator()() const::{lambda(long)#1}, std::array<char*, 2ul>, TrivialOffsetCalculator<1, unsigned int>, TrivialOffsetCalculator<1, unsigned int>, at::native::memory::LoadWithCast<1>, at::native::memory::StoreWithCast<1>)": 1,
    "void at::native::reduce_kernel<512, 1, at::native::ReduceOp<long, at::native::func_wrapper_t<long, at::native::sum_functor<long, long, long>::operator()(at::TensorIterator&)::{lambda(long, long)#1}>, unsigned int, long, 4, 4> >(at::native::ReduceOp<long, at::native::func_wrapper_t<long, at::native::sum_functor<long, long, long>::operator()(at::TensorIterator&)::{lambda(long, long)#1}>, unsigned int, long, 4, 4>)": 1,
    "triton_red_fused_add_mul_native_layer_norm_slice_split_unsqueeze_0": 32,
    "_quantize_rows": 224,
    "_ZN7cutlass13device_kernelIN2at4cuda6detail34enable_3x_kernel_for_sm10_or_laterINS_4gemm6kernel13GemmUniversalIN4cute5tupleIJiiiEEENS5_10collective13CollectiveMmaINS5_31MainloopSm120TmaWarpSpecializedILi2ELi2ENS9_IJNS8_1CILi1EEESF_SF_EEENS5_40KernelTmaWarpSpecializedCooperativeSm120ILi2EEEEENS9_IJNSE_ILi128EEESK_SK_EEENS_12float_e4m3_tENS9_IJlSF_lEEESM_SN_NS8_8TiledMMAINS8_8MMA_AtomIJNS8_16SM120_16x8x32_TNISM_SM_fEEEEENS8_6LayoutINS9_IJNSE_ILi4EEENSE_ILi2EEESF_EEENS9_IJSF_SU_NSE_ILi0EEEEEEEENS9_IJSK_NSE_ILi32EEES10_EEEEENS8_13SM90_TMA_LOADENS8_14ComposedLayoutINS8_7SwizzleILi3ELi4ELi3EEENS8_18smem_ptr_flag_bitsILi8EEENST_INS9_IJNSE_ILi8EEESK_EEENS9_IJSK_SF_EEEEEEENS8_9Copy_AtomIJNS8_17SM75_U32x4_LDSM_NEhEEENS8_8identityES13_S1D_S1G_S1H_EENS_8epilogue10collective18CollectiveEpilogueINS1J_22Sm90TmaWarpSpecializedILi2ELi2ELi4ELb0ELb1EEEJSL_NS9_IJNSE_ILi64EEES10_EEEvSN_NS_10bfloat16_tESN_NS1J_6fusion15Sm90TreeVisitorINS1R_11Sm90ComputeINS1J_6thread8IdentityES1Q_fLNS_15FloatRoundStyleE2EvEEJNS1S_INS1T_INS_4plusEffLS1W_2EvEEJNS1R_16Sm90RowBroadcastILi0ESL_ffNS9_IJSX_SF_SX_EEELi4ELb1EEENS1S_INS1T_INS_10multipliesEffLS1W_2EvEEJS22_NS1S_IS24_JNS1R_16Sm90ColBroadcastILi0ESL_ffNS9_IJSF_SX_SX_EEELi4ELb1EEENS1R_12Sm90AccFetchEEEEEEEEEEEEES13_NS14_INS15_ILi2ELi4ELi3EEENS17_ILi16EEENST_INS9_IJS19_S10_EEENS9_IJS10_SF_EEEEEEENS8_17SM75_U32x2_LDSM_NENS8_14SM90_TMA_STOREES2I_NS8_17SM90_U32x2_STSM_NENS1E_IJS2L_NS_6half_tEEEEvEEEvvEEEEEEvNT_6ParamsE": 224,
    "triton_per_fused__to_copy_mean_pow_view_1": 64,
    "triton_poi_fused__to_copy_add_mean_mul_pow_rsqrt_select_sub_unsqueeze_view_2": 64,
    "triton_poi_fused__scaled_dot_product_flash_attention__to_copy_cat_stack_transpose_view_3": 32,
    "triton_poi_fused__scaled_dot_product_flash_attention__to_copy_cat_stack_transpose_view_4": 32,
    "triton_poi_fused__scaled_dot_product_flash_attention__to_copy_cat_stack_transpose_view_5": 32,
    "void pytorch_flash::flash_fwd_kernel<Flash_fwd_kernel_traits<128, 128, 64, 4, false, false, cutlass::bfloat16_t, Flash_kernel_traits<128, 128, 64, 4, cutlass::bfloat16_t> >, false, false, false, false, false, true, false, false>(pytorch_flash::Flash_fwd_params)": 32,
    "triton_red_fused_add_mul_native_layer_norm_slice_split_tanh_unsqueeze_view_6": 32,
    "triton_poi_fused_mul_silu_view_7": 32,
    "triton_poi_fused_add_mul_slice_split_tanh_unsqueeze_view_8": 32,
    "void at::native::elementwise_kernel<128, 4, at::native::gpu_kernel_impl_nocast<at::native::(anonymous namespace)::where_kernel_impl(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(bool, unsigned short, unsigned short)#1}>(at::TensorIteratorBase&, at::native::(anonymous namespace)::where_kernel_impl(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(bool, unsigned short, unsigned short)#1} const&)::{lambda(int)#1}>(int, at::native::gpu_kernel_impl_nocast<at::native::(anonymous namespace)::where_kernel_impl(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(bool, unsigned short, unsigned short)#1}>(at::TensorIteratorBase&, at::native::(anonymous namespace)::where_kernel_impl(at::TensorIterator&)::{lambda()#1}::operator()() const::{lambda()#2}::operator()() const::{lambda(bool, unsigned short, unsigned short)#1} const&)::{lambda(int)#1})": 1,
    "void at::native::(anonymous namespace)::vectorized_layer_norm_kernel<c10::BFloat16, float, false>(int, float, c10::BFloat16 const*, c10::BFloat16 const*, c10::BFloat16 const*, float*, float*, c10::BFloat16*)": 1,
    "void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctorOnSelf_add<c10::BFloat16>, std::array<char*, 2ul>, false>(int, at::native::CUDAFunctorOnSelf_add<c10::BFloat16>, std::array<char*, 2ul>)": 1,
    "void at::native::vectorized_elementwise_kernel<4, at::native::BinaryFunctor<c10::BFloat16, c10::BFloat16, c10::BFloat16, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 3ul>, false>(int, at::native::BinaryFunctor<c10::BFloat16, c10::BFloat16, c10::BFloat16, at::native::binary_internal::MulFunctor<float> >, std::array<char*, 3ul>)": 1,
    "void cutlass::Kernel2<cutlass_80_tensorop_bf16_s16816gemm_relu_bf16_64x128_64x3_tn_align8>(cutlass_80_tensorop_bf16_s16816gemm_relu_bf16_64x128_64x3_tn_align8::Params)": 1
  },
  "transformer_calls": 40,
  "full_denoising_steps": 40
}