[legacy] clean up legacy code (#4743)

* [legacy] remove outdated codes of pipeline (#4692)

* [legacy] remove cli of benchmark and update optim (#4690)

* [legacy] remove cli of benchmark and update optim

* [doc] fix cli doc test

* [legacy] fix engine clip grad norm

* [legacy] remove outdated colo tensor (#4694)

* [legacy] remove outdated colo tensor

* [test] fix test import

* [legacy] move outdated zero to legacy (#4696)

* [legacy] clean up utils (#4700)

* [legacy] clean up utils

* [example] update examples

* [legacy] clean up amp

* [legacy] fix amp module

* [legacy] clean up gpc (#4742)

* [legacy] clean up context

* [legacy] clean core, constants and global vars

* [legacy] refactor initialize

* [example] fix examples ci

* [example] fix examples ci

* [legacy] fix tests

* [example] fix gpt example

* [example] fix examples ci

* [devops] fix ci installation

* [example] fix examples ci

colossalai/legacy/zero/shard_utils/base_shard_strategy.py

@@ -0,0 +1,22 @@
+from abc import ABC, abstractmethod
+from typing import List, Optional
+
+import torch.distributed as dist
+
+from colossalai.legacy.zero.sharded_param.sharded_tensor import ShardedTensor
+
+
+class BaseShardStrategy(ABC):
+
+    def __init__(self) -> None:
+        """Abstract Shard Strategy. Use to shard a tensors on multiple GPUs.
+        """
+        super().__init__()
+
+    @abstractmethod
+    def shard(self, tensor_list: List[ShardedTensor], process_group: Optional[dist.ProcessGroup] = None):
+        pass
+
+    @abstractmethod
+    def gather(self, tensor_list: List[ShardedTensor], process_group: Optional[dist.ProcessGroup] = None):
+        pass