TestHandleFromDLPack(status, ctx, {4}, {});
  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});

  return true;
}

// Copies `src_graph` into `dst_graph`. Any node in `src_graph` with input
// `src_inputs[i]` will have that input replaced with `dst_inputs[i]`.  `prefix`
// will be prepended to copied node names. `control_deps` are nodes in
// `dst_graph` that the copied `src_graph` nodes will have control dependencies
// on. `return_nodes` are nodes in `src_graph`, and the new corresponding nodes

                          /*expected_max_outputs=*/1, status.get());
  EXPECT_NE(TF_GetCode(status.get()), TF_CANCELLED);
  EXPECT_EQ(TF_GetCode(status.get()), TF_INVALID_ARGUMENT);
  EXPECT_THAT(TF_Message(status.get()), HasSubstr("assertion failed"));

  // Note that future collectives with the same context do not work at the
  // moment; once canceled, the collective executor requires the program to be
  // restarted / context to be reset.
}

  // 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

    for (int i = 0; i < grad_outputs.size(); i++) {
      auto grad_input = grad_outputs[i];
      // TODO(srbs): Should we add a copy contructor to AbstractTensorHandle
      // that takes care of this similar to `Tensor`?
      if (grad_input) {
        grad_input->Ref();
      }
      grad_inputs[i] = grad_input;
    }
    return absl::OkStatus();
  }

                       const char* dst, TF_Status* status) {
  // If target is a directory return TF_FAILED_PRECONDITION.
  // Target might be missing, so don't error in that case.
  struct stat st;
  if (stat(dst, &st) != 0) {
    if (errno != ENOENT) {
      TF_SetStatusFromIOError(status, errno, dst);
      return;
    }
  } else if (S_ISDIR(st.st_mode)) {

  EXPECT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);

  // Create a new tensor_handle.
  TFE_TensorHandle* h0_task0_new = TestMatrixTensorHandle(ctx);

  // Check that copying it to the old remote device (named localhost) fails.
  TFE_TensorHandleCopyToDevice(h0_task0_new, ctx, remote_device_name, status);
  EXPECT_NE(TF_OK, TF_GetCode(status)) << TF_Message(status);

}

TEST(TensorPjRtBufferUtilTest, GetPjRtCBufferFromTensorNoBuffer) {
  auto allocator = std::make_unique<AsyncValueAllocator>();
  tensorflow::Tensor tensor(allocator.get(), DT_FLOAT, {1});

  EXPECT_THAT(
      GetPjRtCBufferFromTensor(&tensor),
      StatusIs(error::INTERNAL, HasSubstr(absl::StrCat(
                                    "Input tensor does not have PjRtBuffer"))));
}

      ExecutionState::kIdle;
  // Tells the worker thread that there is new work.
  tensorflow::condition_variable start_execute_;
  // The worker thread notifies that work has finished.
  tensorflow::condition_variable finished_execute_;
  // Notifies a StartExecute that the previous Join has finished.
  tensorflow::condition_variable finished_join_;

  TFE_TensorHandle* h0 = TestVariable(ctx, 1.0, task1_name);
  TFE_TensorHandle* h1 = TestVariable(ctx, 2.0, task2_name);
  TFE_TensorHandle* h2 = TestVariable(ctx, 3.0, task0_name);

  // Add a sync point to make sure that variables have been initialized
  // before the function execution starts.
  TFE_ContextAsyncWait(ctx, status);
  EXPECT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);