F0907 14:48:53.222919 3532398 reduction.cc:147] Check failed: LayoutUtil::IsMonotonicWithDim0Major( hero.instruction().operand(i)->shape().layout()) reduction-layout-normalizer must run before code generation
*** Check failure stack trace: ***
    @     0x7fc781ba56f4  absl::lts_20230802::log_internal::LogMessage::SendToLog()
    @     0x7fc781ba55f4  absl::lts_20230802::log_internal::LogMessage::Flush()
    @     0x7fc781ba5a99  absl::lts_20230802::log_internal::LogMessageFatal::~LogMessageFatal()
    @     0x7fc77dcedf4e  xla::gpu::(anonymous namespace)::ReductionEmitter::ReductionEmitter()
    @     0x7fc77dced0d7  xla::gpu::ReductionFusion::EmitInitializers()
    @     0x7fc77edbaeda  xla::gpu::KernelFusionEmitterBase::Emit()
    @     0x7fc77dc6a88a  xla::gpu::IrEmitterUnnested::EmitFusion()
    @     0x7fc77dc75214  xla::gpu::IrEmitterUnnested::EmitHloInstruction()
    @     0x7fc77dc55d3e  xla::gpu::IrEmitterUnnested::EmitHloComputation()
    @     0x7fc77dc595f5  xla::gpu::IrEmitterUnnested::EmitCommandBufferThunk()
    @     0x7fc77dc75076  xla::gpu::IrEmitterUnnested::EmitHloInstruction()
    @     0x7fc77dc55d3e  xla::gpu::IrEmitterUnnested::EmitHloComputation()
    @     0x7fc77dc6c87b  xla::gpu::IrEmitterUnnested::BuildWhileThunk()
    @     0x7fc77dc6c606  xla::gpu::IrEmitterUnnested::EmitWhile()
    @     0x7fc77dc753a2  xla::gpu::IrEmitterUnnested::EmitHloInstruction()
    @     0x7fc77dc55d3e  xla::gpu::IrEmitterUnnested::EmitHloComputation()
    @     0x7fc77dc553c8  xla::gpu::IrEmitterUnnested::EmitConditional()
    @     0x7fc77dc750f5  xla::gpu::IrEmitterUnnested::EmitHloInstruction()
    @     0x7fc77dc55d3e  xla::gpu::IrEmitterUnnested::EmitHloComputation()
    @     0x7fc77dc6c87b  xla::gpu::IrEmitterUnnested::BuildWhileThunk()
    @     0x7fc77dc6c606  xla::gpu::IrEmitterUnnested::EmitWhile()
    @     0x7fc77dc753a2  xla::gpu::IrEmitterUnnested::EmitHloInstruction()
    @     0x7fc77dc55d3e  xla::gpu::IrEmitterUnnested::EmitHloComputation()
    @     0x7fc77d960c01  xla::gpu::CompileModuleToLlvmIr()
    @     0x7fc77d827f4f  xla::gpu::GpuCompiler::CompileToBackendResult()
    @     0x7fc77d82b25d  xla::gpu::GpuCompiler::RunBackend()
    @     0x7fc77d5aee85  xla::Service::BuildExecutable()
    @     0x7fc77d53a368  xla::LocalService::CompileExecutables()
    @     0x7fc77d52dcf4  xla::LocalClient::Compile()
    @     0x7fc77d4d6568  xla::PjRtStreamExecutorClient::Compile()
    @     0x7fc77d47983d  xla::StreamExecutorGpuClient::Compile()
    @     0x7fc77d4d7070  xla::PjRtStreamExecutorClient::Compile()
    @     0x7fc77d439df7  std::__detail::__variant::__gen_vtable_impl<>::__visit_invoke()
    @     0x7fc77d4297dc  pjrt::PJRT_Client_Compile()
    @     0x7fc791dd5bba  xla::InitializeArgsAndCompile()
    @     0x7fc791dd608e  xla::PjRtCApiClient::Compile()
    @     0x7fc796da1a9b  xla::ifrt::PjRtLoadedExecutable::Create()
    @     0x7fc796d9cf01  xla::ifrt::PjRtCompiler::Compile()
    @     0x7fc796607fae  xla::PyClient::CompileIfrtProgram()
    @     0x7fc796608c7b  xla::PyClient::Compile()
    @     0x7fc796610a2e  nanobind::detail::func_create<>()::{lambda()#1}::__invoke()
    @     0x7fc7981597ad  nanobind::detail::nb_func_vectorcall_complex()
    @     0x7fc86096a5a2  nanobind::detail::nb_bound_method_vectorcall()
    @     0x55e485740fbf  PyObject_Vectorcall
Aborted