support pytorch lightning 1.7

README.md

@@ -93,7 +93,7 @@ ray.init("ray://<head_node_host>:10001")
 ```
 Now you can run your training script on the laptop, but have it execute as if your laptop has all the resources of the cluster essentially providing you with an **infinite laptop**.
 
-**Note:** When using with Ray Client, you must disable checkpointing and logging for your Trainer by setting `checkpoint_callback` and `logger` to `False`.
+**Note:** When using with Ray Client, you must disable checkpointing and logging for your Trainer by setting `enable_checkpointing` and `logger` to `False`.
 
 ## Horovod Strategy on Ray
 Or if you prefer to use Horovod as the distributed training protocol, use the `HorovodRayStrategy` instead.

ray_lightning/accelerators/delayed_gpu_accelerator.py

@@ -16,10 +16,10 @@
 import torch
 
 from pytorch_lightning.accelerators import Accelerator,\
-    GPUAccelerator
+    CUDAAccelerator
 
 
-class _GPUAccelerator(GPUAccelerator):
+class _GPUAccelerator(CUDAAccelerator):
     """Accelerator for GPU devices.
 
     adapted from:

ray_lightning/examples/ray_ddp_sharded_example.py

@@ -57,6 +57,8 @@ def download_data():
         num_workers=num_workers, use_gpu=use_gpu, init_hook=download_data)
 
     dm = MNISTDataModule(data_dir, batch_size=batch_size)
+    dm.train_transforms = None
+    dm.val_transforms = None
 
     model = ImageGPT(
         embed_dim=embed_dim, layers=16, heads=4, vocab_size=32, num_pixels=28)
@@ -130,4 +132,4 @@ def download_data():
             batch_size=args.batch_size,
             embed_dim=args.embed_dim,
             max_epochs=args.num_epochs,
-            max_steps=None)
+            max_steps=-1)

ray_lightning/examples/ray_ddp_tune.py

@@ -31,11 +31,13 @@ def download_data():
     trainer = pl.Trainer(
         max_epochs=num_epochs,
         callbacks=callbacks,
-        progress_bar_refresh_rate=0,
+        enable_progress_bar=False,
         strategy=RayStrategy(
             num_workers=num_workers, use_gpu=use_gpu, init_hook=download_data))
     dm = MNISTDataModule(
         data_dir=data_dir, num_workers=1, batch_size=config["batch_size"])
+    dm.train_transforms = None
+    dm.val_transforms = None
     trainer.fit(model, dm)
 
 

ray_lightning/ray_ddp.py

@@ -283,8 +283,3 @@ def distributed_sampler_kwargs(self):
     def _is_single_process_single_device(self):
         """Return True if the process is single process and single device."""
         return True
-
-    def teardown(self) -> None:
-        """Teardown the workers and pytorch DDP connections."""
-        self.accelerator = None
-        super().teardown()

ray_lightning/ray_horovod.py

@@ -127,7 +127,6 @@ def world_size(self) -> int:
     def teardown(self) -> None:
         """Teardown the strategy."""
         self.join()
-        self.accelerator = None
         super().teardown()
 
     @property

requirements-test.txt

@@ -4,7 +4,7 @@ flake8-comprehensions
 flake8-quotes
 yapf==0.23.0
 pytest
-pytorch-lightning==1.6.4
+pytorch-lightning==1.7.1
 lightning-bolts==0.3.3
 ray[tune]
 torch==1.12.0

setup.py

@@ -3,10 +3,10 @@
 setup(
     name="ray_lightning",
     packages=find_packages(where=".", include="ray_lightning*"),
-    version="0.3.0",
+    version="0.4.0",
     author="Ray Team",
     description="Ray distributed strategies for Pytorch Lightning.",
     long_description="Custom Pytorch Lightning distributed strategies "
     "built on top of distributed computing framework Ray.",
     url="https://github.com/ray-project/ray_lightning_accelerators",
-    install_requires=["pytorch-lightning==1.6.*", "ray"])
+    install_requires=["pytorch-lightning==1.7.*", "ray"])