Skip to content

Conversation

@pan-x-c
Copy link
Collaborator

@pan-x-c pan-x-c commented Oct 21, 2025

Description

  1. Remove deprecated fields in buffer config
  2. Replace runner_num with runner_per_engine
  3. Rename ppo_max_token_len_per_gpu to max_token_len_per_gpu

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

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @pan-x-c, 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!

This pull request streamlines the configuration for the Buffer and Explorer components by consolidating related settings, removing outdated parameters, and updating all relevant examples and documentation. The primary goal is to simplify the configuration experience and ensure consistency with current best practices, making the system easier to understand and use.

Highlights

  • Configuration Refactoring: The pull request significantly refactors the configuration structure for 'Buffer' and 'Explorer' components, moving default_workflow_type and default_reward_fn_type to be nested directly within the taskset configuration under buffer or rollout_args, rather than at a higher level.
  • Deprecated Field Removal: Several deprecated configuration fields have been removed, including system_prompt, reply_prefix, mm_data_kwargs, sft_warmup_dataset, and sft_warmup_steps, along with their associated deprecation warnings.
  • Explorer Runner Configuration Update: The explorer.runner_num configuration parameter has been replaced with explorer.runner_per_model across various example and tutorial files, indicating a change in how explorer runners are specified.
  • Documentation Updates: Documentation files, including both English and Chinese versions of tutorials and configuration guides, have been updated to reflect the new configuration structure and the removal of deprecated fields.
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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

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.

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 simplifies buffer and explorer configurations by refactoring several parameters. The changes move default settings for workflow and reward functions to be more closely associated with tasksets, and removes several deprecated or redundant fields like sft_warmup_*, system_prompt, and reply_prefix from the configuration classes. The runner_num parameter is also consistently renamed to runner_per_model across various example and documentation files.

The code changes in Python files are clean and effectively centralize configuration logic. The updates to the YAML configuration files across the examples are consistent with these changes.

My review focuses on the documentation, where I found a few inconsistencies and minor errors. Specifically, there are discrepancies in runner_per_model values between the English and Chinese documentation, an incomplete item in one of the markdown files, and an inconsistent example. Addressing these will improve the clarity and correctness of the documentation.

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Oct 21, 2025

/unittest-all

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
160 157 0 3 0 0 3.5s

Skipped

Tests Status
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_std_grpo 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_step_wise_grpo_advantage 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_duplicate_grpo 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_advantage 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_correct_bias 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_reward_std 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_step_wise_grpo_advantage 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/experience_pipeline_test.py::TestExperiencePipeline::test_experience_pipeline 13ms
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_experience_buffer 4ms
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_0_sft 6ms
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_1_dpo 6ms
tests/buffer/file_test.py::TestFileBuffer::test_file_reader 1ms
tests/buffer/file_test.py::TestFileBuffer::test_file_writer 3ms
tests/buffer/formatter_test.py::TestFormatter::test_dpo_messages_formatter 1ms
tests/buffer/formatter_test.py::TestFormatter::test_dpo_plaintext_formatter 1ms
tests/buffer/formatter_test.py::TestFormatter::test_multi_modal_sft_formatter 1ms
tests/buffer/formatter_test.py::TestFormatter::test_sft_messages_formatter 1ms
tests/buffer/formatter_test.py::TestFormatter::test_sft_plaintext_formatter 1ms
tests/buffer/formatter_test.py::TestFormatter::test_task_formatter 1ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_buffer_reuse 8ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_capacity 4ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_reuse_count_control 6ms
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_0_queue 5ms
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_1_priority_queue 5ms
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_capacity 6ms
tests/buffer/reward_shaping_mapper_test.py::TestRewardShapingMapper::test_basic_usage 1ms
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_buffer_read_write 4ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_0 1ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_1 3ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_2 1ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_3 3ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_4 1ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_5 4ms
tests/cli/launcher_test.py::TestLauncherMain::test_debug_mode 36ms
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_command 7ms
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_in_dlc 1ms
tests/cli/launcher_test.py::TestLauncherMain::test_main_studio_command 1ms
tests/cli/launcher_test.py::TestLauncherMain::test_multi_stage_run 1ms
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 32ms
tests/common/config_test.py::TestConfig::test_config_flatten 1ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 1ms
tests/common/config_test.py::TestConfig::test_load_default_config 13ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 1ms
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_hf_datasets_conversion 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_gather_experiences_with_custom_fields 1ms
tests/common/experience_test.py::TestExperienceConversion::test_multiturn_experience_batch_converstion 1ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate 55ms
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 36ms
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 46ms
tests/common/vllm_test.py::TestModelLen_0::test_model_len 21ms
tests/common/vllm_test.py::TestModelLen_1::test_model_len 20ms
tests/common/vllm_test.py::TestAPIServer::test_api 24ms
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 24ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask 1ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 1ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 22ms
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 20ms
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 53ms
tests/explorer/explorer_test.py::TestExplorerCountdownNoEval::test_explorer 59ms
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 206ms
tests/explorer/explorer_test.py::ServeTest::test_serve 69ms
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 5ms
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 5ms
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results 24ms
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 8ms
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 14ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_0 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_reward_propagation_workflow_1 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_0 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_step_wise_reward_workflow_1 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_raise_error 1ms
tests/explorer/step_wise_workflow_test.py::WorkflowTest::test_workflows_stop_at_max_env_steps 1ms
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_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_1 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_1 1ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_0::test_multi_turn_workflow 19ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 19ms
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter ⏭️ 1ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 1ms
tests/manager/synchronizer_test.py::TestSynchronizerExit::test_synchronizer 32ms
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_0::test_synchronizer 73ms
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_1::test_synchronizer 78ms
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_2::test_synchronizer 122ms
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_3::test_synchronizer 119ms
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_0::test_synchronizer 72ms
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_1::test_synchronizer 72ms
tests/service/data_juicer_test.py::TestDataJuicer::test_config 1ms
tests/service/data_juicer_test.py::TestDataJuicer::test_server_start 21ms
tests/service/data_juicer_test.py::TestDataJuicerExperiencePipeline::test_data_juicer_operators 23ms
tests/service/data_juicer_test.py::TestDataJuicerTaskPipeline::test_data_juicer_task_pipeline 14ms
tests/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer 139ms
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 262ms
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 48ms
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 54ms
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 53ms
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 57ms
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 60ms
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer 100ms
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 40ms
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 36ms
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 36ms
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 76ms
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 78ms
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 142ms
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 95ms
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 317ms
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 56ms
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer ⏭️ 1ms
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer ⏭️ 1ms
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 138ms
tests/utils/eval_utils_test.py::TestComputeScore::test_both_boxed_and_equivalent 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_both_boxed_and_not_equivalent 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_empty_ground_truth 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_empty_solution_string 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_multiple_boxed_answers_in_solution 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_boxed_truth_raw_and_equivalent 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_boxed_truth_raw_and_not_equivalent 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_not_boxed 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_solution_raw_and_ground_truth_boxed_equivalent 1ms
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/log_test.py::LogTest::test_actor_log 5ms
tests/utils/log_test.py::LogTest::test_group_by_node 4ms
tests/utils/log_test.py::LogTest::test_no_actor_log 1ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_local 1ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_remote 9ms
tests/utils/plugin_test.py::TestPluginLoader::test_passing_custom_class 5ms

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Oct 22, 2025

/unittest-module-common

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
33 33 0 0 0 0 316ms

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 33ms
tests/common/config_test.py::TestConfig::test_config_flatten 1ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 1ms
tests/common/config_test.py::TestConfig::test_default_workflow 1ms
tests/common/config_test.py::TestConfig::test_load_default_config 3ms
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 1ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 1ms
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_hf_datasets_conversion 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_gather_experiences_with_custom_fields 1ms
tests/common/experience_test.py::TestExperienceConversion::test_multiturn_experience_batch_converstion 1ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate 56ms
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 36ms
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 44ms
tests/common/vllm_test.py::TestModelLen_0::test_model_len 21ms
tests/common/vllm_test.py::TestModelLen_1::test_model_len 20ms
tests/common/vllm_test.py::TestAPIServer::test_api 24ms
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 24ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask 1ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 1ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 22ms
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 20ms

Github Test Reporter by CTRF 💚

@hiyuchang hiyuchang merged commit cd101e1 into modelscope:main Oct 22, 2025
2 checks 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.

3 participants