distinct kernels: 97 total GPU us: 553403.1010000036
{'other': 273.4, 'GEMM(other)': 81.8, 'FP4-related': 198.2} (ms)
--- top 25 kernels by time ---
   130.2 ms    672x  [FP4-related] cutlass3x_sm120_bstensorop_s16864gemm_block_scaled_ue4m3xe2m1_ue4m3xe2m1_f32_bf16_bf16_128x128x256_1x1x1_0_tnn_align32_o_vs16_bias_bf16_relu
    71.5 ms    216x  [GEMM(other)] std::enable_if<!(false), void>::type internal::gemvx::kernel<int, int, __nv_bfloat16, __nv_bfloat16, __nv_bfloat16, float, false, true, true, false, 7
    67.4 ms    672x  [FP4-related] cutlass3x_sm120_bstensorop_s16864gemm_block_scaled_ue4m3xe2m1_ue4m3xe2m1_f32_bf16_bf16_128x128x256_1x1x1_0_tnn_align32_o_vs16_bias_bf16_relu_stream_k
    41.3 ms  46080x  [other] void at::native::elementwise_kernel<128, 2, at::native::gpu_kernel_impl_nocast<at::native::CUDAFunctor_add<float> >(at::TensorIteratorBase&, at::nativ
    23.7 ms  23616x  [other] void at::native::vectorized_elementwise_kernel<4, at::native::exp_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#2}
    23.4 ms  23040x  [other] void at::native::vectorized_elementwise_kernel<4, at::native::log_kernel_cuda(at::TensorIteratorBase&)::{lambda()#2}::operator()() const::{lambda()#2}
    22.8 ms  23040x  [other] void at::native::vectorized_elementwise_kernel<4, at::native::(anonymous namespace)::masked_fill_kernel(at::TensorIterator&, c10::Scalar const&)::{lam
    21.8 ms  23040x  [other] void at::native::vectorized_elementwise_kernel<4, at::native::CUDAFunctor_add<float>, std::array<char*, 3ul>, false>(int, at::native::CUDAFunctor_add<
    21.4 ms  23040x  [other] void at::native::vectorized_elementwise_kernel<4, at::native::AbsFunctor<float>, std::array<char*, 2ul>, false>(int, at::native::AbsFunctor<float>, st
    21.2 ms  11520x  [other] void at::native::reduce_kernel<256, 2, at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::MaxNanFunctor<float> >, unsigned int,
    21.0 ms  23040x  [other] void at::native::vectorized_elementwise_kernel<4, at::native::AUnaryFunctor<float, float, bool, at::native::(anonymous namespace)::CompareEqFunctor<fl
    20.6 ms  11520x  [other] void at::native::reduce_kernel<256, 2, at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::ope
    18.1 ms  11520x  [other] void at::native::reduce_kernel<512, 1, at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::MaxNanFunctor<float> >, unsigned int,
    17.2 ms  11520x  [other] void at::native::reduce_kernel<512, 1, at::native::ReduceOp<float, at::native::func_wrapper_t<float, at::native::sum_functor<float, float, float>::ope
     3.4 ms     96x  [GEMM(other)] void sgemm_largek_lds64<true, false, 5, 5, 4, 4, 4, 34>(float*, float const*, float const*, int, int, int, int, int, int, float const*, float const*, 
     2.6 ms    210x  [other] fused_recurrent_gated_delta_rule_packed_decode_kernel
     2.3 ms   1092x  [other] void tensorrt_llm::kernels::quantize_with_block_size<(tensorrt_llm::BlockScaleQuantizationType)0, __nv_bfloat16, 16, false, false, false, false, std::
     1.7 ms   1728x  [other] void at::native::vectorized_elementwise_kernel<4, at::native::bfloat16_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda(float)#1}, std::array<char*,
     1.4 ms    480x  [GEMM(other)] void dot_kernel<float, 128, 0, cublasDotParams<cublasGemvTensorStridedBatched<float const>, cublasGemvTensorStridedBatched<float> > >(cublasDotParams<
     1.3 ms    576x  [other] void at::native::reduce_kernel<512, 1, at::native::ReduceOp<float, at::native::MeanOps<float, float, float, float>, unsigned int, float, 4, 4> >(at::n
     1.3 ms    577x  [other] void at::native::unrolled_elementwise_kernel<at::native::direct_copy_kernel_cuda(at::TensorIteratorBase&)::{lambda()#3}::operator()() const::{lambda()
     1.3 ms     96x  [GEMM(other)] void cutlass::Kernel2<cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_32x1_nn_align2>(cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_32x1_n
     1.2 ms    576x  [other] void at::native::elementwise_kernel<128, 4, at::native::gpu_kernel_impl_nocast<at::native::BinaryFunctor<c10::BFloat16, c10::BFloat16, c10::BFloat16, 
     1.1 ms    588x  [GEMM(other)] kernel_cutlass_kernel_flashinfernormkernelsrmsnormRMSNormKernel_object_at__tensorptrbf16gmemalign128oi64409640961_tensorptrbf16gmemalign16o40961_tenso
     1.0 ms    480x  [GEMM(other)] void cutlass::Kernel2<cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_16x16_32x1_nn_align2>(cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_16x16_32x1_n