Skip to content

Conversation

@chenyushuo
Copy link
Collaborator

@chenyushuo chenyushuo commented Aug 6, 2025

Description

As the title says.

Checklist

Please check the following items before code is ready to be reviewed.

  • Code has passed all tests
  • Docstrings have been added/updated in Google Style
  • Documentation has been updated
  • Code is ready for review

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Summary of Changes

Hello @chenyushuo, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

I've implemented a significant improvement to the Synchronizer actor's lifecycle management. Previously, its existence was tied to manual acquire and release calls. Now, the Synchronizer will automatically detect when its dependent modules, such as the Trainer and Explorer, are no longer active and will gracefully terminate itself. This change streamlines resource management and reduces the potential for orphaned actors.

Highlights

  • Automatic Synchronizer Lifecycle: The Synchronizer actor now automatically terminates when all associated Trainer and Explorer modules are no longer running, replacing the previous manual reference counting mechanism.
  • Synchronizer Module Tracking: The Synchronizer's constructor now accepts a reference to the module that creates it, and it continuously monitors the liveness of all registered modules to determine when to exit.
  • Simplified Module Shutdown: Manual acquire and release calls for the Synchronizer have been removed from Trainer and Explorer classes, simplifying their shutdown procedures.
  • New Liveness Checks: Trainer and Explorer classes now include an is_alive method, which the Synchronizer uses to check their operational status.
  • New Test Coverage: A new test case, TestSynchronizerExit, has been added to validate the correct automatic termination behavior of the Synchronizer.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in issue comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments or fill out our survey to provide feedback.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

@chenyushuo
Copy link
Collaborator Author

/unittest-all

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces an automatic lifecycle management for the Synchronizer actor by tracking its client modules and exiting when all of them have terminated. This is a solid improvement over the previous manual reference counting system. My review includes suggestions to enhance the robustness and clarity of the implementation, such as using a set to track modules and employing more specific exception handling. Additionally, I've pointed out a potential flakiness issue in the new test case and suggested a way to make it more reliable.

@github-actions
Copy link

github-actions bot commented Aug 6, 2025

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
88 88 0 0 0 0 2.1s

Tests

Test Name Status Flaky Duration
tests/algorithm/add_strategy_test.py::TestAddStrategy::test_correct_bias_strategy 1ms
tests/algorithm/add_strategy_test.py::TestAddStrategy::test_duplicate_add_strategy 1ms
tests/algorithm/add_strategy_test.py::TestAddStrategy::test_grpo_args 1ms
tests/algorithm/add_strategy_test.py::TestAddStrategy::test_reward_variance_strategy 1ms
tests/algorithm/add_strategy_test.py::TestAddStrategy::test_step_wise_grpo_strategy 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_dpo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_gspo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_mix_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_opmd_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_ppo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_sft_policy_loss 1ms
tests/buffer/file_test.py::TestFileBuffer::test_file_buffer 3ms
tests/buffer/file_test.py::TestFileBuffer::test_file_reader 1ms
tests/buffer/file_test.py::TestFileBuffer::test_file_writer 2ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_buffer_reuse 7ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_capacity 3ms
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_0_queue 4ms
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_1_priority_queue 4ms
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_capacity 4ms
tests/buffer/sql_test.py::TestSQLBuffer::test_create_sql_buffer 5ms
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 1ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 1ms
tests/common/config_test.py::TestConfig::test_load_default_config 7ms
tests/common/experience_test.py::TestEID::test_eid_properties 1ms
tests/common/experience_test.py::TestExperience::test_action_mask_and_logprobs_type 1ms
tests/common/experience_test.py::TestExperience::test_assertions 1ms
tests/common/experience_test.py::TestExperience::test_dpo_experience 1ms
tests/common/experience_test.py::TestExperience::test_gather 1ms
tests/common/experience_test.py::TestExperience::test_multi_turn_experience 1ms
tests/common/experience_test.py::TestExperience::test_serialize_deserialize 1ms
tests/common/experience_test.py::TestExperience::test_single_turn_experience 1ms
tests/common/experience_test.py::TestExperience::test_to_dict 1ms
tests/common/experience_test.py::TestExperienceConversion::test_batch_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_dpo_experience_batch_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_experience_model_experience_conversion 1ms
tests/common/experience_test.py::TestExperienceConversion::test_multiturn_experience_batch_converstion 1ms
tests/common/synchronizer_test.py::TestSynchronizerExit::test_synchronizer 19ms
tests/common/synchronizer_test.py::TestStateDictBasedSynchronizer_0::test_synchronizer 89ms
tests/common/synchronizer_test.py::TestStateDictBasedSynchronizer_1::test_synchronizer 87ms
tests/common/synchronizer_test.py::TestStateDictBasedSynchronizer_2::test_synchronizer 139ms
tests/common/synchronizer_test.py::TestStateDictBasedSynchronizer_3::test_synchronizer 160ms
tests/common/synchronizer_test.py::TestNCCLBasedSynchronizer_0::test_synchronizer 62ms
tests/common/synchronizer_test.py::TestNCCLBasedSynchronizer_1::test_synchronizer 63ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate 40ms
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 49ms
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 52ms
tests/common/vllm_test.py::ModelWrapperTest_3::test_generate 38ms
tests/common/vllm_test.py::ModelWrapperTest_4::test_generate 50ms
tests/common/vllm_test.py::TestAPIServer::test_api 29ms
tests/common/vllm_test.py::TestTokenizer::test_assistant_token_mask 1ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 24ms
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 21ms
tests/explorer/explorer_test.py::BaseExplorerCase::test_explorer 1ms
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 96ms
tests/explorer/explorer_test.py::TestExplorerCountdownNoEval::test_explorer 94ms
tests/explorer/explorer_test.py::TestExplorerWithAddStrategy::test_explorer 62ms
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 4ms
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results 20ms
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 5ms
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 5ms
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 15ms
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 9ms
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 8ms
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 5ms
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 7ms
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 13ms
tests/explorer/workflow_test.py::WorkflowTest::test_gsm8k_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_rm_gallery_workflow 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable 1ms
tests/trainer/trainer_test.py::BaseTrainerCase::test_trainer 1ms
tests/trainer/trainer_test.py::TestTrainerCountdown::test_trainer 224ms
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 89ms
tests/trainer/trainer_test.py::TestTrainerGSM8K::test_trainer 61ms
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer 78ms
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 46ms
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 44ms
tests/trainer/trainer_test.py::TestFullyAsyncMode::test_fully_async_mode_0_queue 92ms
tests/trainer/trainer_test.py::TestFullyAsyncMode::test_fully_async_mode_1_priority_queue 88ms
tests/utils/eval_utils_test.py::TestMathEvalUtils::test_extract_answer 1ms
tests/utils/eval_utils_test.py::TestMathEvalUtils::test_verify_math_answer 1ms
tests/utils/eval_utils_test.py::TestEvalUtils::test_is_equiv 1ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins 5ms

Github Test Reporter by CTRF 💚

@pan-x-c pan-x-c merged commit e97a633 into modelscope:main Aug 7, 2025
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants