mirror of
https://github.com/volcengine/verl.git
synced 2025-10-20 21:53:50 +08:00
b00f77d855
> [!WARNING]
> We are [immigrating to `ruff` as the linter and formatter and
`pre-commit` as the managing
tool](https://github.com/volcengine/verl/pull/1010).
>
> If your branch is based on a previous commit using `yapf` and
`pylint`, simply merging might trigger overwhelming linting errors,
while **you are only expected to resolve ones in the files related to
your PR**.
>
> To resolve this issue, please try the following workaround to only
include the files you **really changed** in the PR:
>
> 1. In your branch, fix linting and format with `ruff`: `ruff check
--fix && ruff-format`
> 2. Squash into a single commit in a new branch: `git reset --soft
$(git merge-base main HEAD) && git add -A && git commit -m "feat: ..."`
> 3. Merge with the latest main: `git merge origin/main`
> 4. Force push to your branch: `git push --force`
We add the reminder above to the documentation to tell contributors how
to avoid overwhelming linting errors.
### Motivation
According to dicussion in #896, this PR immigrates from yapf & pylint to
ruff based on pre-commit, which allows unified version control and
automatic hook on committing.
### Summary
The `pre-commit` hook and CI
- checks staged / committed files in commits / PR's
- checks all files each month (This should fail before we fix all the
files by the ruff standard)
### Explanation for the Failing CI Workflow `pre-commit`
For now, we only apply `ruff format` and `ruff check --fix` **without
resolving all the errors**, since there are too many errors to resolve,
which causes the CI workflow `pre-commit` fails.
For resolving the remaining errors, we leave to future commits.
Specifically, the `pre-commit` hook and CI will require every commit to
fix its related files with `ruff`, which will fix all the files
incrementally.
### Reviewing Suggestion
The commit
3d93f51ba8
is huge since we apply `ruff` to all the files. To review the main
changes, please check the commits before and after it.
84 lines
2.7 KiB
Python
84 lines
2.7 KiB
Python
# Copyright 2024 Bytedance Ltd. and/or its affiliates
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import ray
|
|
|
|
from verl import DataProto
|
|
from verl.single_controller.base import Worker
|
|
from verl.single_controller.base.decorator import Dispatch, register
|
|
from verl.single_controller.ray.base import (
|
|
RayClassWithInitArgs,
|
|
RayResourcePool,
|
|
RayWorkerGroup,
|
|
create_colocated_worker_cls,
|
|
)
|
|
|
|
|
|
@ray.remote
|
|
class Actor(Worker):
|
|
def __init__(self) -> None:
|
|
super().__init__()
|
|
|
|
@register(dispatch_mode=Dispatch.DP_COMPUTE_PROTO)
|
|
def add(self, data: DataProto):
|
|
data.batch["a"] += self.rank
|
|
return data
|
|
|
|
|
|
@ray.remote
|
|
class Critic(Worker):
|
|
def __init__(self, config) -> None:
|
|
super().__init__()
|
|
self.config = config
|
|
|
|
@register(dispatch_mode=Dispatch.DP_COMPUTE_PROTO)
|
|
def sub(self, data: DataProto):
|
|
data.batch["a"] -= self.config["b"]
|
|
return data
|
|
|
|
|
|
def test_colocated_workers():
|
|
ray.init()
|
|
|
|
import torch
|
|
|
|
data = DataProto.from_dict({"a": torch.zeros(10)})
|
|
# create separate workers on the same resource pool
|
|
actor_cls = RayClassWithInitArgs(cls=Actor)
|
|
critic_cls = RayClassWithInitArgs(cls=Critic, config={"b": 10})
|
|
resource_pool = RayResourcePool(process_on_nodes=[2])
|
|
|
|
actor_wg = RayWorkerGroup(resource_pool=resource_pool, ray_cls_with_init=actor_cls)
|
|
critic_wg = RayWorkerGroup(resource_pool=resource_pool, ray_cls_with_init=critic_cls)
|
|
|
|
expected_actor_output = actor_wg.add(data)
|
|
expected_critic_output = critic_wg.sub(data)
|
|
|
|
# create colocated workers
|
|
cls_dict = {"actor": actor_cls, "critic": critic_cls}
|
|
ray_cls_with_init = create_colocated_worker_cls(cls_dict)
|
|
wg_dict = RayWorkerGroup(resource_pool=resource_pool, ray_cls_with_init=ray_cls_with_init)
|
|
spawn_wg = wg_dict.spawn(prefix_set=cls_dict.keys())
|
|
|
|
colocated_actor_wg = spawn_wg["actor"]
|
|
colocated_critic_wg = spawn_wg["critic"]
|
|
|
|
actor_output = colocated_actor_wg.add(data)
|
|
critic_output = colocated_critic_wg.sub(data)
|
|
|
|
torch.testing.assert_close(expected_actor_output.batch, actor_output.batch, atol=0, rtol=0)
|
|
torch.testing.assert_close(expected_critic_output.batch, critic_output.batch, atol=0, rtol=0)
|
|
|
|
ray.shutdown()
|