args

docs/source/common/optimizers.rst

@@ -300,8 +300,6 @@ override the :meth:`optimizer_step` function.
 
 For example, here step optimizer A every 2 batches and optimizer B every 4 batches
 
-.. note:: When using Trainer(enable_pl_optimizer=True), there is no need to call `.zero_grad()`.
-
 .. testcode::
 
     def optimizer_zero_grad(self, current_epoch, batch_idx, optimizer, opt_idx):

pytorch_lightning/core/lightning.py

@@ -1324,9 +1324,6 @@ def optimizer_step(
         By default, Lightning calls ``step()`` and ``zero_grad()`` as shown in the example
         once per optimizer.
 
-        .. tip:: With ``Trainer(enable_pl_optimizer=True)``, you can use ``optimizer.step()`` directly
-         and it will handle zero_grad, accumulated gradients, AMP, TPU and more automatically for you.
-
         Warning:
             If you are overriding this method, make sure that you pass the ``optimizer_closure`` parameter
             to ``optimizer.step()`` function as shown in the examples. This ensures that

tests/plugins/test_rpc_sequential_plugin.py

@@ -42,7 +42,6 @@ def test_rpc_sequential_plugin_manual(tmpdir, args=None):
         gpus=2,
         distributed_backend="ddp",
         plugins=[RPCSequentialPlugin(balance=[2, 1], rpc_timeout_sec=5 * 60)],
-        enable_pl_optimizer=True,
     )
 
     trainer.fit(model)

tests/utilities/test_all_gather_grad.py

@@ -89,7 +89,6 @@ def training_epoch_end(self, outputs) -> None:
         max_epochs=1,
         log_every_n_steps=1,
         accumulate_grad_batches=2,
-        enable_pl_optimizer=True,
         gpus=2,
         accelerator="ddp",
     )