Skip to content

Conversation

@chenyushuo
Copy link
Collaborator

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

@gemini-code-assist
Copy link
Contributor

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!

This pull request significantly refactors the configuration validation and update mechanisms within the system. By introducing a modular validator pattern, it extracts complex validation logic from the main Config class into dedicated, reusable components. This change enhances the maintainability, extensibility, and clarity of the configuration handling, making it easier to add new validation rules or modify existing ones without impacting the core configuration structure.

Highlights

  • Modular Configuration Validation: The monolithic check_and_update method in the Config class has been refactored into a series of distinct validator classes, each responsible for a specific aspect of configuration validation.
  • New config_validator.py Module: A new module trinity/common/config_validator.py has been introduced. It defines an abstract ConfigValidator base class and several concrete implementations, such as GlobalConfigValidator, RayClusterConfigValidator, and ModelConfigValidator.
  • Simplified Config Class: The Config class is now cleaner, delegating its validation logic to the new validator system. It also includes a new get_gpu_allocation_info method for centralized GPU resource calculation.
  • Refactored verl_config.py: The synchronize_config method in veRLConfig has been updated to leverage the new get_gpu_allocation_info method and a new _adjust_token_len_if_needed helper, improving readability and maintainability.
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 introduces a significant and well-executed refactoring of the configuration validation logic. By moving the validation logic from the monolithic Config class into a new config_validator.py with a set of modular ConfigValidator classes, the code is now much cleaner, more maintainable, and easier to extend. The use of helper methods and loops in verl_config.py to reduce code duplication is also a great improvement. I've found one potential bug and a minor style improvement. Overall, excellent work on improving the codebase's structure and quality.

@chenyushuo
Copy link
Collaborator Author

/gemini review

@chenyushuo
Copy link
Collaborator Author

/unittest-module-common

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 a significant and valuable refactoring of the configuration validation logic by moving it into a new config_validator.py module. This change greatly improves modularity and maintainability by breaking down a large validation method into smaller, dedicated validator classes. The related changes in verl_config.py also contribute to better code structure by centralizing GPU allocation logic. Overall, this is a very positive change for the codebase. I have identified a couple of issues in the new implementation: one concerning the execution order of validators which could lead to incorrect resource allocation, and a logic bug in verl_config.py introduced during refactoring. Please see my specific comments for details.

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
42 41 0 1 0 0 15m 55s

Skipped

Tests Status
tests/common/vllm_test.py::TestTinkerAsyncAPIServer::test_api_async skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 41.6s
tests/common/config_test.py::TestConfig::test_chat_template_path 76ms
tests/common/config_test.py::TestConfig::test_config_flatten 32ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 481ms
tests/common/config_test.py::TestConfig::test_default_workflow 75ms
tests/common/config_test.py::TestConfig::test_load_default_config 5.5s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 75ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 77ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 1.7s
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_gather_with_token_level_reward 1ms
tests/common/experience_test.py::TestExperience::test_hf_datasets_conversion 15ms
tests/common/experience_test.py::TestExperience::test_multi_turn_experience 1ms
tests/common/experience_test.py::TestExperience::test_serialize_deserialize 2ms
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 1m 28s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 1m 13s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 40.8s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 1m 6s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 57.8s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 56.8s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 57.9s
tests/common/vllm_test.py::TestAPIServer::test_api 28.4s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 57.4s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 28.0s
tests/common/vllm_test.py::TestTinkerAsyncAPIServer::test_api_async ⏭️ 1ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask 351ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 348ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 58.7s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 57.1s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 2m 29s
tests/common/vllm_test.py::TestTinkerAPI::test_tinker_api 1m 17s

Github Test Reporter by CTRF 💚

@chenyushuo
Copy link
Collaborator Author

/unittest-all

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
235 226 1 8 0 0 1h 14m

Failed Tests

Failed Tests ❌ Fail Message
❌ tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode The test failed in the call phase

Skipped

Tests Status
tests/common/vllm_test.py::TestTinkerAsyncAPIServer::test_api_async skipped ⏭️
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter_v1 skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestTinkerTrainer::test_trainer skipped ⏭️
tests/trainer/trainer_test.py::TestTinkerTrainer::test_trainer_class skipped ⏭️
tests/trainer/trainer_test.py::AgentScopeTunerTest::test_agentscope_tuner skipped ⏭️
tests/utils/swanlab_test.py::TestSwanlabMonitor::test_swanlab_monitor_smoke skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_std_grpo 41ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_step_wise_grpo_advantage 3ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_duplicate_grpo 4ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_advantage 3ms
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/advantage_fn_test.py::TestGroupedAdvantageFn::test_step_wise_grpo_with_std_threshold 2ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_abs_kl_fn 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_corrected_k3_fallback 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_corrected_k3_loss 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_corrected_k3_same_policy 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_corrected_k3_with_old_logprob 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_dummy_kl_fn 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_k1_kl_fn 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_k2_kl_fn 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_k3_kl_fn 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_kl_loss_aggregation_modes 1ms
tests/algorithm/kl_fn_test.py::KLFnTest::test_low_var_kl_fn 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_dpo_policy_loss 2ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_gspo_policy_loss 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_mix_policy_loss 3ms
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_ppo_policy_loss_with_sequence_masking 1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_sapo_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 15.0s
tests/buffer/experience_pipeline_test.py::TestExperiencePipeline::test_pass_rate_calculation 6.7s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_experience_buffer 2.9s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_0_sft 4.9s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_1_dpo 6.1s
tests/buffer/file_test.py::TestFileBuffer::test_file_reader 181ms
tests/buffer/file_test.py::TestFileBuffer::test_file_writer 1.9s
tests/buffer/formatter_test.py::TestFormatter::test_dpo_messages_formatter 590ms
tests/buffer/formatter_test.py::TestFormatter::test_dpo_plaintext_formatter 467ms
tests/buffer/formatter_test.py::TestFormatter::test_multi_modal_sft_formatter 899ms
tests/buffer/formatter_test.py::TestFormatter::test_sft_messages_formatter 1.0s
tests/buffer/formatter_test.py::TestFormatter::test_sft_plaintext_formatter 731ms
tests/buffer/formatter_test.py::TestFormatter::test_task_formatter 226ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_buffer_reuse 6.6s
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_capacity 2.6s
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_reuse_count_control 4.7s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_0_queue 3.7s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_1_priority_queue 3.7s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_capacity 4.0s
tests/buffer/reader_test.py::TestBufferReader::test_buffer_reader_registration 545ms
tests/buffer/reward_shaping_mapper_test.py::TestRewardShapingMapper::test_basic_usage 7ms
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_default_queue_default_sample_strategy 2.0s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_default_queue_staleness_control_sample_strategy 2.2s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_priority_queue_default_sample_strategy 2.2s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_priority_queue_staleness_control_sample_strategy 2.3s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_0::test_sql_staleness_control_sample_strategy 5.0s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_default_queue_default_sample_strategy 2.0s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_default_queue_staleness_control_sample_strategy 2.0s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_priority_queue_default_sample_strategy 2.2s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_priority_queue_staleness_control_sample_strategy 2.0s
tests/buffer/sample_strategy_test.py::ExperienceStorageTest_1::test_sql_staleness_control_sample_strategy 4.1s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_exp_buffer_read_write_0 5.8s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_exp_buffer_read_write_1 3.1s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_task_buffer_read_write 3.3s
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_0 73ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_1 58ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_2 90ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_3 90ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_4 89ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_5 93ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_6 108ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_simple 46ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_0_file 61ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_1_sql 3.2s
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_2_file 40ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_3_sql 3.6s
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_4_file 40ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_5_sql 3.6s
tests/cli/launcher_test.py::TestLauncherMain::test_debug_mode 1m 14s
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_command 6.1s
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_in_dlc 1.4s
tests/cli/launcher_test.py::TestLauncherMain::test_main_studio_command 300ms
tests/cli/launcher_test.py::TestLauncherMain::test_multi_stage_run 3.9s
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 31.9s
tests/common/config_test.py::TestConfig::test_chat_template_path 74ms
tests/common/config_test.py::TestConfig::test_config_flatten 31ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 644ms
tests/common/config_test.py::TestConfig::test_default_workflow 72ms
tests/common/config_test.py::TestConfig::test_load_default_config 4.1s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 76ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 73ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 145ms
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_gather_with_token_level_reward 1ms
tests/common/experience_test.py::TestExperience::test_hf_datasets_conversion 15ms
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 1m 13s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 1m 6s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 1m 12s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 52.3s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 21.5s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 51.6s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 57.0s
tests/common/vllm_test.py::TestAPIServer::test_api 24.4s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 51.5s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 23.9s
tests/common/vllm_test.py::TestTinkerAsyncAPIServer::test_api_async ⏭️ 1ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask 266ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 246ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 53.4s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 22.1s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 1m 27s
tests/common/vllm_test.py::TestTinkerAPI::test_tinker_api 1m 13s
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 51.6s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer 1m 22s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 3m 32s
tests/explorer/explorer_test.py::ServeTest::test_serve 1m 31s
tests/explorer/proxy_test.py::RecorderTest::test_recorder 86ms
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 5.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout 13.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results 20.8s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1 5.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1 5.9s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 5.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 5.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_min_wait 9.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 15.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 10.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 8.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 25.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 8.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 14.0s
tests/explorer/scheduler_test.py::TestRunnerStateCollection::test_runner_state_collection 10.4s
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 602ms
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 1.0s
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 1.0s
tests/explorer/workflow_test.py::WorkflowTest::test_gsm8k_workflow 12ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 17ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 136ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 3ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 11ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 7ms
tests/explorer/workflow_test.py::WorkflowTest::test_rm_gallery_workflow 121ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_1 101ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_0 1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_resettable_1 201ms
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_0::test_multi_turn_workflow 20.7s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 20.3s
tests/explorer/workflow_test.py::TestWorkflowStateRecording::test_workflow_state_recording 4.0s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter_v0 722ms
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter_v1 ⏭️ 2ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 137ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_get_state 8.0s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_with_openai 22.6s
tests/manager/synchronizer_test.py::TestSynchronizerExit::test_synchronizer 1m 21s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_0::test_synchronizer 1m 15s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_1::test_synchronizer 1m 22s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_2::test_synchronizer 1m 57s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_3::test_synchronizer 1m 22s
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_0::test_synchronizer 1m 9s
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_1::test_synchronizer 1m 9s
tests/service/data_juicer_test.py::TestDataJuicer::test_config 1.2s
tests/service/data_juicer_test.py::TestDataJuicer::test_server_start 21.6s
tests/service/data_juicer_test.py::TestDataJuicerExperiencePipeline::test_data_juicer_operators 20.9s
tests/service/data_juicer_test.py::TestDataJuicerTaskPipeline::test_data_juicer_task_pipeline 13.8s
tests/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer 2m 40s
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 4m 23s
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 1m 37s
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 50.8s
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 48.8s
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 53.2s
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 1m
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer 1m 56s
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 34.2s
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 31.8s
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 32.8s
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 1m 40s
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 1m 30s
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 627ms
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 2m 14s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 5m 23s
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 1m 37s
tests/trainer/trainer_test.py::TestServeWithTrainer::test_serve_with_trainer 1m 52s
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer ⏭️ 564ms
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer ⏭️ 812ms
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 2m 46s
tests/trainer/trainer_test.py::TestOverRollout::test_trainer 48.2s
tests/trainer/trainer_test.py::TestTrainerPromptTruncation::test_trainer 1m 14s
tests/trainer/trainer_test.py::TestTinkerTrainer::test_trainer ⏭️ 1ms
tests/trainer/trainer_test.py::TestTinkerTrainer::test_trainer_class ⏭️ 1ms
tests/trainer/trainer_test.py::AgentScopeTunerTest::test_agentscope_tuner ⏭️ 1ms
tests/utils/eval_utils_test.py::TestComputeScore::test_both_boxed_and_equivalent 10ms
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 2ms
tests/utils/eval_utils_test.py::TestMathEvalUtils::test_verify_math_answer 61ms
tests/utils/eval_utils_test.py::TestEvalUtils::test_is_equiv 4ms
tests/utils/log_test.py::LogTest::test_actor_log 2.0s
tests/utils/log_test.py::LogTest::test_group_by_node 1.9s
tests/utils/log_test.py::LogTest::test_no_actor_log 649ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_local_0__workspace_tests_utils_plugins 80ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_local_1_tests_utils_plugins 76ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_remote_0__workspace_tests_utils_plugins 9.1s
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_remote_1_tests_utils_plugins 9.3s
tests/utils/plugin_test.py::TestPluginLoader::test_passing_custom_class_0__workspace_tests_utils_plugins 5.2s
tests/utils/plugin_test.py::TestPluginLoader::test_passing_custom_class_1_tests_utils_plugins 5.0s
tests/utils/registry_test.py::TestRegistryWithRay::test_dynamic_import 2.8s
tests/utils/registry_test.py::TestRegistry::test_algorithm_registry_mapping 3ms
tests/utils/registry_test.py::TestRegistry::test_buffer_module_registry_mapping 1ms
tests/utils/registry_test.py::TestRegistry::test_common_module_registry_mapping 55ms
tests/utils/registry_test.py::TestRegistry::test_register_module 1ms
tests/utils/registry_test.py::TestRegistry::test_utils_module_registry_mapping 1ms
tests/utils/swanlab_test.py::TestSwanlabMonitor::test_swanlab_monitor_smoke ⏭️ 1ms

Github Test Reporter by CTRF 💚

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.

1 participant