A.reset(A_raw);
  }
  // Bias
  float Bias_vals[] = {2.0f, 3.0f};
  int64_t Bias_dims[] = {2};
  AbstractTensorHandlePtr Bias;
  {
    AbstractTensorHandle* Bias_raw;
    status_ = TestTensorHandleWithDims<float, TF_FLOAT>(
        immediate_execution_ctx_.get(), Bias_vals, Bias_dims, 1, &Bias_raw);
    ASSERT_EQ(errors::OK, status_.code()) << status_.message();
    Bias.reset(Bias_raw);
  }

    TF_RETURN_IF_ERROR(forward_attrs_.Get("data_format", &data_format));

    // Grad for A
    grad_inputs[0] = upstream_grad;
    grad_inputs[0]->Ref();

    // Grad for bias
    std::string name = "bias_add_grad";
    TF_RETURN_IF_ERROR(BiasAddGrad(ctx, upstream_grad, &grad_inputs[1],
                                   data_format.c_str(), name.c_str()));

    return absl::OkStatus();
  }

            supports equivalent functionality. `max_tokens` argument renamed to
            `num_tokens`.
        *   `Discretization` added `num_bins` argument for learning bins
            boundaries through calling `adapt` on a dataset. Renamed `bins`
            argument to `bin_boundaries` for specifying bins without `adapt`.
    *   Improvements to model saving/loading:
        *   `model.load_weights` now accepts paths to saved models.

 	goto no_more_room;
diff --git a/string/bits/string2.h b/string/bits/string2.h
index c9bf593..f461fc1 100644
--- a/string/bits/string2.h
+++ b/string/bits/string2.h
@@ -47,29 +47,7 @@
 #endif
 
 #if _STRING_ARCH_unaligned
-/* If we can do unaligned memory accesses we must know the endianess.  */
-# include <endian.h>
 # include <bits/types.h>
-
-# if __BYTE_ORDER == __LITTLE_ENDIAN

  switch (dtype.code) {
    case DLDataTypeCode::kDLBool:
      if (dtype.bits != 8) {
        return tensorflow::errors::InvalidArgument(
            "Only DLPack bools of bitwidth 8 are supported, got: ", dtype.bits);
      }
      *tf_dtype = TF_DataType::TF_BOOL;
      return absl::OkStatus();

    case DLDataTypeCode::kDLUInt:
      switch (dtype.bits) {
        case 8:
          *tf_dtype = TF_DataType::TF_UINT8;

  EXPECT_EQ(dltensor_out->ndim, dltensor_in->ndim);
  EXPECT_EQ(dltensor_out->dtype.code, dltensor_in->dtype.code);
  EXPECT_EQ(dltensor_out->dtype.bits, dltensor_in->dtype.bits);
  EXPECT_EQ(dltensor_out->dtype.lanes, dltensor_in->dtype.lanes);
  for (int i = 0; i < dltensor_in->ndim; ++i) {
    EXPECT_EQ(dltensor_out->shape[i], dltensor_in->shape[i]);
    if (dltensor_out->strides) {

index 98c080b..843bd45 100644
--- a/locale/xlocale.h
+++ b/locale/xlocale.h
@@ -20,6 +20,9 @@
 #ifndef _XLOCALE_H
 #define _XLOCALE_H	1
 
+#ifndef _BITS_TYPES___LOCALE_T_H
+#define _BITS_TYPES___LOCALE_T_H 1
+
 /* Structure for reentrant locale using functions.  This is an
    (almost) opaque type for the user level programs.  The file and