Skip to content

Conversation

@pan-x-c
Copy link
Collaborator

@pan-x-c pan-x-c commented Dec 12, 2025

Description

This PR add supports for vLLM v0.12.0.

However, we found a significant performance drop in v0.12.0 compared to v0.11.0, with the test time increasing from 9 minutes to 12 minutes.

So, we still recommend using v0.10.2 or v0.11.0.

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 primarily focuses on a significant upgrade of the vLLM library to version 0.12.0 and its Ray dependency to 2.50.0. This update is accompanied by an upgrade of the underlying CUDA environment in the Docker images to 13.0.2. To ensure seamless integration and continued functionality with the new vLLM version, the changes include the implementation of version-specific patching mechanisms for vLLM's API server and worker components. Additionally, a new enable_thinking parameter has been introduced in the ModelWrapper for enhanced model control, particularly for Qwen3 models, and an existing patch for prompt logprobs calculation has been refined for accuracy.

Highlights

  • vLLM and Ray Dependency Upgrade: The core vLLM library has been updated to version 0.12.0, and the Ray dependency has been bumped to 2.50.0, ensuring compatibility with the latest features and bug fixes.
  • CUDA Base Image Update: All Dockerfiles (Dockerfile, Dockerfile.megatron, Dockerfile.uv) now use the nvcr.io/nvidia/cuda:13.0.2-cudnn-devel-ubuntu22.04 base image, upgrading the CUDA environment.
  • Version-Specific vLLM Patching: New conditional logic and a dedicated patch file (api_patch_v12.py) have been introduced to handle API server and worker component differences between vLLM versions, specifically for v0.12.0 and older versions.
  • New enable_thinking Parameter: A new enbale_thinking (likely a typo for enable_thinking) parameter has been added to the ModelWrapper for potential use with Qwen3 series models, allowing for more nuanced control over model behavior.
  • Improved Prompt Logprobs Calculation: The vLLM worker patch now correctly applies temperature scaling to logits when calculating prompt logprobs, addressing a potential inaccuracy in previous vLLM versions.
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 updates vLLM to v0.12.0 and ray to v2.50.0, which also involves upgrading the CUDA version in the Dockerfiles. The code modifications are mainly to ensure compatibility with the new vLLM version, introducing version-specific logic for API server and worker patches. My review has identified a few areas for improvement: there's a recurring typo in a new parameter name, some type hints could be restored for better code quality, a docstring needs correction, and there's a significant amount of duplicated code that could be refactored. Apart from these points, the changes are logical and well-aligned with the goal of the dependency update.

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 12, 2025

/unittest-module-common

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
40 36 4 0 0 0 8m 43s

Failed Tests

Failed Tests ❌ Fail Message
❌ tests/common/vllm_test.py::TestAPIServer::test_api The test failed in the call phase
❌ tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async The test failed in the call phase due to an assertion error
❌ tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls The test failed in the call phase
❌ tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls The test failed in the call phase

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 42.2s
tests/common/config_test.py::TestConfig::test_chat_template_path 375ms
tests/common/config_test.py::TestConfig::test_config_flatten 42ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 193ms
tests/common/config_test.py::TestConfig::test_default_workflow 93ms
tests/common/config_test.py::TestConfig::test_load_default_config 3.4s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 95ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 93ms
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 58.5s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 32.3s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 43.8s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 15.5s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 15.3s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 15.2s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 15.6s
tests/common/vllm_test.py::TestAPIServer::test_api 15.9s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 15.8s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 19.3s
tests/common/vllm_test.py::TestTokenizer::test_action_mask 270ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 241ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 14.8s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 15.0s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 3m 8s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 12, 2025

/unittest-module-common

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
40 40 0 0 0 0 8m 54s

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 43.4s
tests/common/config_test.py::TestConfig::test_chat_template_path 373ms
tests/common/config_test.py::TestConfig::test_config_flatten 42ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 194ms
tests/common/config_test.py::TestConfig::test_default_workflow 93ms
tests/common/config_test.py::TestConfig::test_load_default_config 3.4s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 98ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 93ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 1.8s
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 58.6s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 32.0s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 43.9s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 15.5s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 15.7s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 15.2s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 15.5s
tests/common/vllm_test.py::TestAPIServer::test_api 20.7s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 15.7s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 20.7s
tests/common/vllm_test.py::TestTokenizer::test_action_mask 234ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 231ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 17.7s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 15.8s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 3m 8s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 12, 2025

/unittest-module-common

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
40 39 1 0 0 0 7m 25s

Failed Tests

Failed Tests ❌ Fail Message
❌ tests/common/vllm_test.py::TestSuperLongGeneration::test_generate The test failed in the call phase due to an exception

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 33.0s
tests/common/config_test.py::TestConfig::test_chat_template_path 97ms
tests/common/config_test.py::TestConfig::test_config_flatten 43ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 196ms
tests/common/config_test.py::TestConfig::test_default_workflow 94ms
tests/common/config_test.py::TestConfig::test_load_default_config 3.6s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 96ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 95ms
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 16ms
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 18s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 39.3s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 53.2s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 23.8s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 23.6s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 23.3s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 23.1s
tests/common/vllm_test.py::TestAPIServer::test_api 28.9s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 23.9s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 29.0s
tests/common/vllm_test.py::TestTokenizer::test_action_mask 269ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 240ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 25.3s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 23.2s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 5.2s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 12, 2025

/unittest-module-common

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 12, 2025

/unittest-module-common

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
40 40 0 0 0 0 11m 32s

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 33.0s
tests/common/config_test.py::TestConfig::test_chat_template_path 97ms
tests/common/config_test.py::TestConfig::test_config_flatten 42ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 197ms
tests/common/config_test.py::TestConfig::test_default_workflow 95ms
tests/common/config_test.py::TestConfig::test_load_default_config 3.4s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 99ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 96ms
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 16ms
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 2ms
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 17s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 40.8s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 50.8s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 23.4s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 23.1s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 23.1s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 22.8s
tests/common/vllm_test.py::TestAPIServer::test_api 28.7s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 23.9s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 28.9s
tests/common/vllm_test.py::TestTokenizer::test_action_mask 233ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 227ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 25.7s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 23.6s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 4m 16s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 12, 2025

/unittest-module-trainer

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 12, 2025

/unittest-all

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 12, 2025

/unittest-all

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
210 206 1 3 0 0 1h 40m

Failed Tests

Failed Tests ❌ Fail Message
❌ tests/explorer/explorer_test.py::ServeTest::test_serve The test failed in the call phase due to an exception

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 42ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_step_wise_grpo_advantage 2ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_duplicate_grpo 5ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_advantage 3ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_correct_bias 2ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_reward_std 1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_step_wise_grpo_advantage 2ms
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 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_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 26.3s
tests/buffer/experience_pipeline_test.py::TestExperiencePipeline::test_pass_rate_calculation 19.8s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_experience_buffer 5.0s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_0_sft 6.9s
tests/buffer/experience_storage_test.py::ExperienceStorageTest::test_sql_storage_1_dpo 7.4s
tests/buffer/file_test.py::TestFileBuffer::test_file_reader 258ms
tests/buffer/file_test.py::TestFileBuffer::test_file_writer 5.3s
tests/buffer/formatter_test.py::TestFormatter::test_dpo_messages_formatter 528ms
tests/buffer/formatter_test.py::TestFormatter::test_dpo_plaintext_formatter 447ms
tests/buffer/formatter_test.py::TestFormatter::test_multi_modal_sft_formatter 855ms
tests/buffer/formatter_test.py::TestFormatter::test_sft_messages_formatter 948ms
tests/buffer/formatter_test.py::TestFormatter::test_sft_plaintext_formatter 698ms
tests/buffer/formatter_test.py::TestFormatter::test_task_formatter 215ms
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_buffer_reuse 10.1s
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_capacity 5.9s
tests/buffer/queue_test.py::TestQueueBuffer::test_priority_queue_reuse_count_control 8.0s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_0_queue 7.0s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_1_priority_queue 7.1s
tests/buffer/queue_test.py::TestQueueBuffer::test_queue_buffer_capacity 7.5s
tests/buffer/reader_test.py::TestBufferReader::test_buffer_reader_registration 613ms
tests/buffer/reward_shaping_mapper_test.py::TestRewardShapingMapper::test_basic_usage 6ms
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_exp_buffer_read_write 4.9s
tests/buffer/sql_test.py::TestSQLBuffer::test_sql_task_buffer_read_write 5.3s
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_0 91ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_1 72ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_2 111ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_3 112ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_4 111ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_5 116ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_6 132ms
tests/buffer/task_scheduler_test.py::TestTaskScheduler::test_task_scheduler_simple 58ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_0_file 72ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_1_sql 5.3s
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_2_file 53ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_3_sql 5.2s
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_4_file 52ms
tests/buffer/task_storage_test.py::TaskStorageTest::test_read_task_5_sql 5.5s
tests/cli/launcher_test.py::TestLauncherMain::test_debug_mode 1m 13s
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_command 6.9s
tests/cli/launcher_test.py::TestLauncherMain::test_main_run_in_dlc 1.4s
tests/cli/launcher_test.py::TestLauncherMain::test_main_studio_command 317ms
tests/cli/launcher_test.py::TestLauncherMain::test_multi_stage_run 1.8s
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 33.0s
tests/common/config_test.py::TestConfig::test_chat_template_path 96ms
tests/common/config_test.py::TestConfig::test_config_flatten 42ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 193ms
tests/common/config_test.py::TestConfig::test_default_workflow 94ms
tests/common/config_test.py::TestConfig::test_load_default_config 10.1s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 98ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 94ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 158ms
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 18ms
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 33s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 39.2s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 51.8s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 24.9s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 23.5s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 24.6s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 24.0s
tests/common/vllm_test.py::TestAPIServer::test_api 29.0s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 24.3s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 29.2s
tests/common/vllm_test.py::TestTokenizer::test_action_mask 239ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 235ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 25.9s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 24.0s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 4m 16s
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 1m 29s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer 1m 31s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 3m 46s
tests/explorer/explorer_test.py::ServeTest::test_serve 2m 45s
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 14.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 14.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout 22.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results 29.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0 14.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1 14.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0 14.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1 14.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 14.8s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 14.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_min_wait 18.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 24.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 27.9s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 18.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 34.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 18.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 23.2s
tests/explorer/scheduler_test.py::TestRunnerStateCollection::test_runner_state_collection 19.1s
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 17ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 27ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 268ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 4ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 17ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 10ms
tests/explorer/workflow_test.py::WorkflowTest::test_rm_gallery_workflow 119ms
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 22.9s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 23.2s
tests/explorer/workflow_test.py::TestWorkflowStateRecording::test_workflow_state_recording 4.0s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter ⏭️ 3ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 303ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_get_state 8.1s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_with_openai 25.3s
tests/manager/synchronizer_test.py::TestSynchronizerExit::test_synchronizer 1m 10s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_0::test_synchronizer 1m 55s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_1::test_synchronizer 2m
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_2::test_synchronizer 2m 39s
tests/manager/synchronizer_test.py::TestStateDictBasedSynchronizer_3::test_synchronizer 2m 52s
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_0::test_synchronizer 1m 54s
tests/manager/synchronizer_test.py::TestNCCLBasedSynchronizer_1::test_synchronizer 1m 55s
tests/service/data_juicer_test.py::TestDataJuicer::test_config 1.9s
tests/service/data_juicer_test.py::TestDataJuicer::test_server_start 22.0s
tests/service/data_juicer_test.py::TestDataJuicerExperiencePipeline::test_data_juicer_operators 33.8s
tests/service/data_juicer_test.py::TestDataJuicerTaskPipeline::test_data_juicer_task_pipeline 14.6s
tests/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer 3m 30s
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 5m 16s
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 1m 50s
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 1m 54s
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 1m 44s
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 1m 46s
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 2m 1s
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer 3m 6s
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 1m 15s
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 1m 11s
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 1m 13s
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 2m 24s
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 2m 23s
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 3m 2s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 3m 2s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 4m 44s
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 3m 20s
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer ⏭️ 811ms
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer ⏭️ 808ms
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 3m 44s
tests/trainer/trainer_test.py::TestOverRollout::test_trainer 1m 46s
tests/trainer/trainer_test.py::TestTrainerPromptTruncation::test_trainer 1m 25s
tests/utils/eval_utils_test.py::TestComputeScore::test_both_boxed_and_equivalent 15ms
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 2ms
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 2ms
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 4ms
tests/utils/eval_utils_test.py::TestMathEvalUtils::test_verify_math_answer 77ms
tests/utils/eval_utils_test.py::TestEvalUtils::test_is_equiv 6ms
tests/utils/log_test.py::LogTest::test_actor_log 5.1s
tests/utils/log_test.py::LogTest::test_group_by_node 4.9s
tests/utils/log_test.py::LogTest::test_no_actor_log 908ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_local_0__workspace_tests_utils_plugins 99ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_local_1_tests_utils_plugins 98ms
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_remote_0__workspace_tests_utils_plugins 25.3s
tests/utils/plugin_test.py::TestPluginLoader::test_load_plugins_remote_1_tests_utils_plugins 25.5s
tests/utils/plugin_test.py::TestPluginLoader::test_passing_custom_class_0__workspace_tests_utils_plugins 13.8s
tests/utils/plugin_test.py::TestPluginLoader::test_passing_custom_class_1_tests_utils_plugins 13.3s
tests/utils/registry_test.py::TestRegistry::test_dynamic_import 5.1s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 15, 2025

/unittest-module-explorer

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
46 45 0 1 0 0 16m 28s

Skipped

Tests Status
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter skipped ⏭️

Tests

Test Name Status Flaky Duration
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer 2m 1s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer 1m 38s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer 3m 44s
tests/explorer/explorer_test.py::ServeTest::test_serve 1m 30s
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow 14.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations 14.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout 22.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results 29.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0 14.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1 14.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0 14.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1 14.2s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution 14.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow 14.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_min_wait 18.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods 24.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop 27.7s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks 18.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid 34.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all 17.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch 22.9s
tests/explorer/scheduler_test.py::TestRunnerStateCollection::test_runner_state_collection 19.4s
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 2ms
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 33ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow 25ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow 559ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow 4ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow 14ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow 8ms
tests/explorer/workflow_test.py::WorkflowTest::test_rm_gallery_workflow 133ms
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 22.8s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow 22.8s
tests/explorer/workflow_test.py::TestWorkflowStateRecording::test_workflow_state_recording 4.0s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter ⏭️ 1ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner 299ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_get_state 8.1s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_with_openai 25.2s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 16, 2025

/unittest-module-common

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
40 40 0 0 0 0 12m 5s

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 42.0s
tests/common/config_test.py::TestConfig::test_chat_template_path 96ms
tests/common/config_test.py::TestConfig::test_config_flatten 42ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 194ms
tests/common/config_test.py::TestConfig::test_default_workflow 94ms
tests/common/config_test.py::TestConfig::test_load_default_config 32.5s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 98ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 95ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 2.0s
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 16ms
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 36s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 40.2s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 55.0s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 24.5s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 24.6s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 23.6s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 24.0s
tests/common/vllm_test.py::TestAPIServer::test_api 29.6s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 24.3s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 30.1s
tests/common/vllm_test.py::TestTokenizer::test_action_mask 246ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 248ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 26.3s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 24.7s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 3m 36s

Github Test Reporter by CTRF 💚

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 16, 2025

/unittest-module-common

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
40 40 0 0 0 0 8m 50s

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid 44.0s
tests/common/config_test.py::TestConfig::test_chat_template_path 96ms
tests/common/config_test.py::TestConfig::test_config_flatten 41ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid 193ms
tests/common/config_test.py::TestConfig::test_default_workflow 93ms
tests/common/config_test.py::TestConfig::test_load_default_config 3.3s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly 95ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation 94ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster 2.0s
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 16ms
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 57.8s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate 31.6s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate 43.8s
tests/common/vllm_test.py::TestModelLen_0::test_model_len 15.5s
tests/common/vllm_test.py::TestModelLen_1::test_model_len 16.0s
tests/common/vllm_test.py::TestModelLen_2::test_model_len 15.5s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len 16.1s
tests/common/vllm_test.py::TestAPIServer::test_api 21.5s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api 16.1s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async 20.8s
tests/common/vllm_test.py::TestTokenizer::test_action_mask 261ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools 256ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls 18.3s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls 15.8s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate 3m 2s

Github Test Reporter by CTRF 💚

@pan-x-c pan-x-c changed the title Update vLLM to v0.12.0 Support vLLM v0.12.0 Dec 16, 2025
@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 16, 2025

/unittest-all

@pan-x-c
Copy link
Collaborator Author

pan-x-c commented Dec 16, 2025

/unittest-module-trainer

@github-actions
Copy link

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
22 20 0 2 0 0 43m 54s

Skipped

Tests Status
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/trainer/trainer_test.py::TestTrainerCountdown_0_fsdp::test_trainer 3m 17s
tests/trainer/trainer_test.py::TestTrainerCountdown_1_megatron::test_trainer 5m 1s
tests/trainer/trainer_test.py::TestStepAheadAsyncRL::test_trainer 1m 33s
tests/trainer/trainer_test.py::TestTrainerGSM8K_0_fsdp::test_trainer 1m 27s
tests/trainer/trainer_test.py::TestTrainerGSM8K_1_fsdp2::test_trainer 1m 20s
tests/trainer/trainer_test.py::TestTrainerGSM8K_2_fsdp::test_trainer 1m 20s
tests/trainer/trainer_test.py::TestTrainerGSM8K_3_fsdp2::test_trainer 1m 35s
tests/trainer/trainer_test.py::TestTrainerSFTWarmupGSM8K::test_trainer 2m 31s
tests/trainer/trainer_test.py::TestTrainerDPO::test_trainer 1m 2s
tests/trainer/trainer_test.py::TestTrainerSFT::test_trainer 57.8s
tests/trainer/trainer_test.py::TestTrainerToolsSFT::test_trainer_tools 59.3s
tests/trainer/trainer_test.py::TestFullyAsyncMode_0_fsdp::test_fully_async_mode 1m 53s
tests/trainer/trainer_test.py::TestFullyAsyncMode_1_fsdp::test_fully_async_mode 1m 53s
tests/trainer/trainer_test.py::TestFullyAsyncMode_2_megatron::test_fully_async_mode 2m 38s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_0_fsdp::test_trainer 2m 17s
tests/trainer/trainer_test.py::TestTrainerCheckpointSave_1_megatron::test_trainer 4m 27s
tests/trainer/trainer_test.py::TestTrainerMIX::test_trainer 2m 32s
tests/trainer/trainer_test.py::TestMultiModalGRPO::test_trainer ⏭️ 809ms
tests/trainer/trainer_test.py::TestMultiModalSFT::test_trainer ⏭️ 808ms
tests/trainer/trainer_test.py::TestTrainerLoRA::test_trainer 4m 11s
tests/trainer/trainer_test.py::TestOverRollout::test_trainer 1m 20s
tests/trainer/trainer_test.py::TestTrainerPromptTruncation::test_trainer 1m 10s

Github Test Reporter by CTRF 💚

@pan-x-c pan-x-c merged commit 8be19eb into modelscope:main Dec 16, 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