mirror of
https://github.com/volcengine/verl.git
synced 2025-10-20 21:53:50 +08:00
bc1b760fb1
### What does this PR do?
- Introduce a separate rolloutworker that can be instantiated without
hybridengine
- Introduce a ModelConfig that wraps all model related config
- Remove hf_rollout (will replace with TP support in the future if
needed)
- Next PR: modify MegatronWorker to use separate rollout worker
### Checklist Before Starting
- [x] Search for similar PRs. Paste at least one query link here: ...
- [x] Format the PR title as `[{modules}] {type}: {description}` (This
will be checked by the CI)
- `{modules}` include `fsdp`, `megatron`, `sglang`, `vllm`, `rollout`,
`trainer`, `ci`, `training_utils`, `recipe`, `hardware`, `deployment`,
`ray`, `worker`, `single_controller`, `misc`, `perf`, `model`, `algo`,
`env`, `tool`, `ckpt`, `doc`, `data`
- If this PR involves multiple modules, separate them with `,` like
`[megatron, fsdp, doc]`
- `{type}` is in `feat`, `fix`, `refactor`, `chore`, `test`
- If this PR breaks any API (CLI arguments, config, function signature,
etc.), add `[BREAKING]` to the beginning of the title.
- Example: `[BREAKING][fsdp, megatron] feat: dynamic batching`
### Test
> For changes that can not be tested by CI (e.g., algorithm
implementation, new model support), validate by experiment(s) and show
results like training curve plots, evaluation results, etc.
### API and Usage Example
> Demonstrate how the API changes if any, and provide usage example(s)
if possible.
```python
# Add code snippet or script demonstrating how to use this
```
### Design & Code Changes
> Demonstrate the high-level design if this PR is complex, and list the
specific changes.
### Checklist Before Submitting
> [!IMPORTANT]
> Please check all the following items before requesting a review,
otherwise the reviewer might deprioritize this PR for review.
- [ ] Read the [Contribute
Guide](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md).
- [ ] Apply [pre-commit
checks](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md#code-linting-and-formatting):
`pre-commit install && pre-commit run --all-files --show-diff-on-failure
--color=always`
- [ ] Add / Update [the
documentation](https://github.com/volcengine/verl/tree/main/docs).
- [ ] Add unit or end-to-end test(s) to [the CI
workflow](https://github.com/volcengine/verl/tree/main/.github/workflows)
to cover all the code. If not feasible, explain why: ...
- [ ] Once your PR is ready for CI, send a message in [the `ci-request`
channel](https://verl-project.slack.com/archives/C091TCESWB1) in [the
`verl` Slack
workspace](https://join.slack.com/t/verl-project/shared_invite/zt-3855yhg8g-CTkqXu~hKojPCmo7k_yXTQ).
(If not accessible, please try [the Feishu group
(飞书群)](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=772jd4f1-cd91-441e-a820-498c6614126a).)
---------
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
69 lines
2.1 KiB
Python
69 lines
2.1 KiB
Python
# Copyright 2025 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.single_controller.base.decorator import Dispatch, register
|
|
from verl.single_controller.base.worker import Worker
|
|
from verl.single_controller.ray.base import RayClassWithInitArgs, RayResourcePool, RayWorkerGroup
|
|
|
|
|
|
class TestActor(Worker):
|
|
# TODO: pass *args and **kwargs is bug prone and not very convincing
|
|
def __init__(self, x) -> None:
|
|
super().__init__()
|
|
self.a = x
|
|
|
|
@register(dispatch_mode=Dispatch.ONE_TO_ALL)
|
|
def get(self):
|
|
return self.a + self.rank
|
|
|
|
|
|
class TestHighLevelActor(Worker):
|
|
def __init__(self, x=None) -> None:
|
|
super().__init__()
|
|
self.test_actor = TestActor(x=x)
|
|
|
|
@register(dispatch_mode=Dispatch.ONE_TO_ALL)
|
|
def get(self):
|
|
return self.test_actor.get()
|
|
|
|
|
|
def test_nested_worker():
|
|
ray.init(num_cpus=100)
|
|
|
|
# create 4 workers, each hold a GPU
|
|
resource_pool = RayResourcePool([4], use_gpu=True)
|
|
class_with_args = RayClassWithInitArgs(cls=ray.remote(TestActor), x=2)
|
|
|
|
worker_group = RayWorkerGroup(
|
|
resource_pool=resource_pool, ray_cls_with_init=class_with_args, name_prefix="worker_group_basic"
|
|
)
|
|
|
|
output = worker_group.get()
|
|
|
|
assert output == [2, 3, 4, 5]
|
|
|
|
class_with_args = RayClassWithInitArgs(cls=ray.remote(TestHighLevelActor), x=2)
|
|
high_level_worker_group = RayWorkerGroup(
|
|
resource_pool=resource_pool, ray_cls_with_init=class_with_args, name_prefix="worker_group_basic_2"
|
|
)
|
|
|
|
output_1 = high_level_worker_group.get()
|
|
|
|
assert output_1 == [2, 3, 4, 5]
|
|
|
|
ray.shutdown()
|