Files
verl/tests/utils/test_nvtx_profile.py
Blue Space 545f899844 [BREAKING] [perf] refactor: Profiler api refactor (#2894)
### What does this PR do?

Refactor profiler CI to a unified way.

TODO:

- nsys use `save_path`
- nsys descrete tests are disabled
- torch profiler

cc: @davidmlw 

### Checklist Before Starting

- [ ] Search for similar PRs. Paste at least one query link here: ...
- [ ] 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

Global profiler config:

```yaml
global_profiler:
  _target_: verl.utils.profiler.ProfilerConfig
  tool: null
  steps: null
  profile_continuous_steps: false
  save_path: outputs/profile
  tool_config:
    nsys:
      _target_: verl.utils.profiler.config.NsightToolConfig
      discrete: false
    npu:
      _target_: verl.utils.profiler.config.NPUToolConfig
      discrete: false
      contents: []
      level: level1
      analysis: true
    torch:
      _target_: verl.utils.profiler.config.TorchProfilerToolConfig
      step_start: 0
      step_end: null
```

Local profiler config:

```yaml
profiler:

  # Required when using verl.utils.omega_conf_to_dataclass to instantiate dataclass configs
  _target_: verl.utils.profiler.ProfilerConfig

  # profiler tool, default same as profiler.tool in global config
  # choices: nsys, npu, torch
  tool: ${oc.select:global_profiler.tool,null}

  # whether enable profile on critic
  enable: False

  # Whether to profile all ranks.
  all_ranks: False

  # The ranks that will be profiled. [] or [0,1,...]
  ranks: []

  # profile results saving path
  save_path: ${oc.select:global_profiler.save_path,null}

  # specific tool config
  tool_config: ${oc.select:global_profiler.tool_config,null}
```

### 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).)
2025-08-11 09:52:41 +08:00

172 lines
7.1 KiB
Python

# Copyright 2024 Bytedance Ltd. and/or its affiliates
# Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
#
# 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 unittest
from unittest.mock import MagicMock, patch
from verl.utils import omega_conf_to_dataclass
from verl.utils.profiler.config import NsightToolConfig, ProfilerConfig
from verl.utils.profiler.nvtx_profile import NsightSystemsProfiler
class TestProfilerConfig(unittest.TestCase):
def test_config_init(self):
import os
from hydra import compose, initialize_config_dir
with initialize_config_dir(config_dir=os.path.abspath("verl/trainer/config")):
cfg = compose(config_name="ppo_trainer")
for config in [
cfg.actor_rollout_ref.actor.profiler,
cfg.actor_rollout_ref.rollout.profiler,
cfg.actor_rollout_ref.ref.profiler,
cfg.critic.profiler,
cfg.reward_model.profiler,
]:
profiler_config = omega_conf_to_dataclass(config)
self.assertEqual(profiler_config.tool, config.tool)
self.assertEqual(profiler_config.enable, config.enable)
self.assertEqual(profiler_config.all_ranks, config.all_ranks)
self.assertEqual(profiler_config.ranks, config.ranks)
self.assertEqual(profiler_config.save_path, config.save_path)
self.assertEqual(profiler_config.ranks, config.ranks)
assert isinstance(profiler_config, ProfilerConfig)
with self.assertRaises(AttributeError):
_ = profiler_config.non_existing_key
assert config.get("non_existing_key") == profiler_config.get("non_existing_key")
assert config.get("non_existing_key", 1) == profiler_config.get("non_existing_key", 1)
def test_frozen_config(self):
"""Test that modifying frozen keys in ProfilerConfig raises exceptions."""
from dataclasses import FrozenInstanceError
from verl.utils.profiler.config import ProfilerConfig
# Create a new ProfilerConfig instance
config = ProfilerConfig(all_ranks=False, ranks=[0], extra={"key": "value"})
with self.assertRaises(FrozenInstanceError):
config.all_ranks = True
with self.assertRaises(FrozenInstanceError):
config.ranks = [1, 2, 3]
with self.assertRaises(TypeError):
config["all_ranks"] = True
with self.assertRaises(TypeError):
config["ranks"] = [1, 2, 3]
assert config["extra"]["key"] == "value"
config["extra"]["key"] = "value2"
assert config["extra"]["key"] == "value2"
class TestNsightSystemsProfiler(unittest.TestCase):
"""Test suite for NsightSystemsProfiler functionality.
Test Plan:
1. Initialization: Verify profiler state after creation
2. Basic Profiling: Test start/stop functionality
3. Discrete Mode: TODO: Test discrete profiling behavior
4. Annotation: Test the annotate decorator in both normal and discrete modes
5. Config Validation: Verify proper config initialization from OmegaConf
"""
def setUp(self):
self.config = ProfilerConfig(enable=True, all_ranks=True)
self.rank = 0
self.profiler = NsightSystemsProfiler(self.rank, self.config, tool_config=NsightToolConfig(discrete=False))
def test_initialization(self):
self.assertEqual(self.profiler.this_rank, True)
self.assertEqual(self.profiler.this_step, False)
def test_start_stop_profiling(self):
with patch("torch.cuda.profiler.start") as mock_start, patch("torch.cuda.profiler.stop") as mock_stop:
# Test start
self.profiler.start()
self.assertTrue(self.profiler.this_step)
mock_start.assert_called_once()
# Test stop
self.profiler.stop()
self.assertFalse(self.profiler.this_step)
mock_stop.assert_called_once()
# def test_discrete_profiling(self):
# discrete_config = ProfilerConfig(discrete=True, all_ranks=True)
# profiler = NsightSystemsProfiler(self.rank, discrete_config)
# with patch("torch.cuda.profiler.start") as mock_start, patch("torch.cuda.profiler.stop") as mock_stop:
# profiler.start()
# self.assertTrue(profiler.this_step)
# mock_start.assert_not_called() # Shouldn't start immediately in discrete mode
# profiler.stop()
# self.assertFalse(profiler.this_step)
# mock_stop.assert_not_called() # Shouldn't stop immediately in discrete mode
def test_annotate_decorator(self):
mock_self = MagicMock()
mock_self.profiler = self.profiler
mock_self.profiler.this_step = True
@NsightSystemsProfiler.annotate(message="test")
def test_func(self, *args, **kwargs):
return "result"
with (
patch("torch.cuda.profiler.start") as mock_start,
patch("torch.cuda.profiler.stop") as mock_stop,
patch("verl.utils.profiler.nvtx_profile.mark_start_range") as mock_start_range,
patch("verl.utils.profiler.nvtx_profile.mark_end_range") as mock_end_range,
):
result = test_func(mock_self)
self.assertEqual(result, "result")
mock_start_range.assert_called_once()
mock_end_range.assert_called_once()
mock_start.assert_not_called() # Not discrete mode
mock_stop.assert_not_called() # Not discrete mode
# def test_annotate_discrete_mode(self):
# discrete_config = ProfilerConfig(discrete=True, all_ranks=True)
# profiler = NsightSystemsProfiler(self.rank, discrete_config)
# mock_self = MagicMock()
# mock_self.profiler = profiler
# mock_self.profiler.this_step = True
# @NsightSystemsProfiler.annotate(message="test")
# def test_func(self, *args, **kwargs):
# return "result"
# with (
# patch("torch.cuda.profiler.start") as mock_start,
# patch("torch.cuda.profiler.stop") as mock_stop,
# patch("verl.utils.profiler.nvtx_profile.mark_start_range") as mock_start_range,
# patch("verl.utils.profiler.nvtx_profile.mark_end_range") as mock_end_range,
# ):
# result = test_func(mock_self)
# self.assertEqual(result, "result")
# mock_start_range.assert_called_once()
# mock_end_range.assert_called_once()
# mock_start.assert_called_once() # Should start in discrete mode
# mock_stop.assert_called_once() # Should stop in discrete mode
if __name__ == "__main__":
unittest.main()