TestHandleFromDLPack(status, ctx, {4}, {1});
  TestHandleFromDLPack(status, ctx, {4, 3, 2}, {});
  TestHandleFromDLPack(status, ctx, {4, 3, 2}, {6, 2, 1});
  // Test that dims with size=1 can have any stride.
  TestHandleFromDLPack(status, ctx, {1}, {1});
  TestHandleFromDLPack(status, ctx, {1}, {0});
  TestHandleFromDLPack(status, ctx, {4, 1, 2}, {2, 1, 1});
  TestHandleFromDLPack(status, ctx, {4, 1, 2}, {2, 0, 1});

  TracingContext* tracing_ctx = dyn_cast<TracingContext>(unwrap(ctx));
  if (!tracing_ctx) {
    tsl::Set_TF_Status_from_Status(
        s, tensorflow::errors::InvalidArgument(
               "Only TracingContext can be converted into a function."));
    return nullptr;
  }
  tsl::Set_TF_Status_from_Status(s,
                                 tracing_ctx->Finalize(unwrap(outputs), &func));
  TF_DeleteExecutionContext(ctx);

  for (int i = 0; i < noutputs; ++i) {
    c_outputs[i] = nullptr;
  }
}

// TF_TensorToTensorV1 decodes a string serialization to DT_RESOURCE.
// In the TFv1 convention, TF_Tensor can hold a string serialization of
// DT_RESOURCE. The string serialization is converted back to a
// ResourceHandle during Session run where the TF_Tensor is converted to a
// Tensor.

TEST(CAPI, TestRemoteExecuteUpdateServerDefResourceAccessAsync) {
  TestRemoteExecuteUpdateServerDefResourceAccess(true);
}

void TestRemoteExecuteUpdateServerDefWithFailures(bool async) {
  // Fail fast on GetStatus requests so we can get errors instead of timeout
  // when updating cluster with non-exsitent worker
  tensorflow::setenv("GRPC_FAIL_FAST", "TRUE", /*overwrite=*/1);

  tensorflow::ServerDef server_def = GetServerDef(2);

  // TODO(b/113217601): This is needed for EagerContext::runner_ to use a
  // threadpool, so that we avoid the possibility of running the runner_ in the
  // threadpool of GPU event mgr, as that can trigger more callbacks to be
  // scheduled on that same threadpool, causing a deadlock in cases where the
  // caller of event_mgr->ThenExecute() blocks on the completion of the callback

      ParallelTensor::FromTensorHandles(parallel_device,
                                        std::move(mixed_handles), status.get());
  ASSERT_TRUE(TF_GetCode(status.get()) == TF_OK);
  // Can't take the shape of a parallel tensor with varying numbers of axes, but
  // running operations on them is OK.
  TF_ASSERT_OK(unknown_length_vector->Shape(&shape));
  EXPECT_THAT(*shape, ElementsAre(-1));

  }
  std::string value_string;
  if (!SummarizeValue(value_string).ok()) {
    value_string = "<error computing value>";
  }
  if (value_string.length() > 100) {
    // The default NumPy-style output can be distractingly long in error
    // messages.
    value_string = absl::StrCat(value_string.substr(0, 100), " [...]");
  }
  Status s;
  const char* device_name = DeviceName(&s);
  if (!s.ok()) {

  int64_t expected_stride = 1;
  for (int i = ndim - 1; i >= 0; --i) {
    // Empty tensors are always compact regardless of strides.
    if (shape_arr[i] == 0) return true;
    // Note that dimensions with size=1 can have any stride.
    if (shape_arr[i] != 1 && stride_arr[i] != expected_stride) {
      valid = false;
    }
    expected_stride *= shape_arr[i];
  }
  return valid;
}
}  // namespace

==============================================================================*/
// This file extends/implements core graph optimizer base classes in terms of
// the C API defined in grappler.h. A class "CSomething" represents a
// "Something" that can be manipulated via calls in the C interface and a C
// struct called "TP_Something".

#include "tensorflow/c/experimental/grappler/grappler.h"

#include <algorithm>
#include <cstddef>
#include <cstring>

  num_retvals = 1;
  executed = false;
  TFE_Execute(matmul.get(), &retval, &num_retvals, status.get());
  EXPECT_FALSE(executed);
  ASSERT_FALSE(TF_GetCode(status.get()) == TF_OK);

  // Custom devices can refuse to do type-based dispatch (as hcustom1 is
  // configured to do)
  matmul.reset(MatMulOp(context.get(), hcustom1.get(), hcpu.get()));
  num_retvals = 1;
  executed = false;