Implement Tinker compatible sample API

[pan-x-c]

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]

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 integrates the Tinker API with vLLM models, providing a standardized interface for model sampling. It includes the necessary tinker dependency and a robust set of tests to ensure the new API's correct behavior across various sampling configurations, enhancing the model's interoperability and ease of use.

Highlights

• Tinker API Integration: Implemented a Tinker-compatible sampling interface for vLLM models, allowing for standardized interaction with the model's generation capabilities.
• New Dependency: Added the tinker library as a project dependency to support the new API integration.
• Comprehensive Testing: Introduced a new test suite (TestTinkerAPI) to thoroughly validate the Tinker API's sampling functionality, including scenarios with and without prompt logprobs and top-k logprobs.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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. ↩

[gemini-code-assist]

Code Review

This pull request introduces a Tinker-compatible sample API for the vLLM model wrapper, adding tinker as a dependency and including a new test suite to validate the API's functionality. The implementation is solid and the tests are thorough. I've provided a few suggestions to enhance robustness, particularly around handling default sampling parameters, and to improve code clarity and maintainability in log-probability processing and test code.

[pan-x-c]

/unittest-module-common

[github-actions]

Summary

Tests 📝	Passed ✅	Failed ❌	Skipped ⏭️	Other ❓	Flaky 🍂	Duration ⏱️
41	40	1	0	0	0	11m 48s

Failed Tests

Failed Tests ❌	Fail Message
❌ tests/common/vllm_test.py::TestLogprobs::test_logprobs_api	The test failed in the call phase due to an assertion error

Tests

Test Name	Status	Flaky	Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid	✅		36.0s
tests/common/config_test.py::TestConfig::test_chat_template_path	✅		67ms
tests/common/config_test.py::TestConfig::test_config_flatten	✅		30ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid	✅		135ms
tests/common/config_test.py::TestConfig::test_default_workflow	✅		65ms
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	✅		65ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation	✅		65ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster	✅		1.9s
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	✅		14ms
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 15s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate	✅		1m 5s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate	✅		34.2s
tests/common/vllm_test.py::TestModelLen_0::test_model_len	✅		51.4s
tests/common/vllm_test.py::TestModelLen_1::test_model_len	✅		21.3s
tests/common/vllm_test.py::TestModelLen_2::test_model_len	✅		57.5s
tests/common/vllm_test.py::TestModelLenWithoutPromptTruncation::test_model_len	✅		51.6s
tests/common/vllm_test.py::TestAPIServer::test_api	✅		54.0s
tests/common/vllm_test.py::TestLogprobs::test_logprobs_api	❌		21.4s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async	✅		23.8s
tests/common/vllm_test.py::TestTokenizer::test_action_mask	✅		300ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools	✅		272ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls	✅		53.2s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls	✅		21.8s
tests/common/vllm_test.py::TestSuperLongGeneration::test_generate	✅		1m 46s
tests/common/vllm_test.py::TestTinkerAPI::test_tinker_api	✅		21.4s

Github Test Reporter by CTRF 💚

[pan-x-c]

/unittest-module-explorer

[github-actions]

Summary

Tests 📝	Passed ✅	Failed ❌	Skipped ⏭️	Other ❓	Flaky 🍂	Duration ⏱️
47	47	0	0	0	0	12m 35s

Tests

Test Name	Status	Flaky	Duration
tests/explorer/explorer_test.py::TestExplorerCountdownEval::test_explorer	✅		1m 31s
tests/explorer/explorer_test.py::TestExplorerGSM8KRULERNoEval::test_explorer	✅		1m 26s
tests/explorer/explorer_test.py::TestExplorerGSM8k::test_explorer	✅		3m 38s
tests/explorer/explorer_test.py::ServeTest::test_serve	✅		1m 24s
tests/explorer/proxy_test.py::RecorderTest::test_recorder	✅		63ms
tests/explorer/scheduler_test.py::SchedulerTest::test_async_workflow	✅		4.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_concurrent_operations	✅		4.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_dynamic_timeout	✅		12.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_get_results	✅		19.5s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_0	✅		4.3s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_non_repeatable_workflow_1	✅		4.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_0	✅		4.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_metric_calculation_with_repeatable_workflow_1	✅		3.9s
tests/explorer/scheduler_test.py::SchedulerTest::test_multi_step_execution	✅		4.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_non_repeatable_workflow	✅		4.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_over_rollout_min_wait	✅		8.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_all_methods	✅		14.0s
tests/explorer/scheduler_test.py::SchedulerTest::test_scheduler_restart_after_stop	✅		7.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_split_tasks	✅		7.6s
tests/explorer/scheduler_test.py::SchedulerTest::test_stepwise_experience_eid	✅		24.4s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all	✅		7.1s
tests/explorer/scheduler_test.py::SchedulerTest::test_wait_all_timeout_with_multi_batch	✅		13.0s
tests/explorer/scheduler_test.py::TestRunnerStateCollection::test_runner_state_collection	✅		9.3s
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	✅		601ms
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	✅		25ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_boxed_workflow	✅		15ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_complex_workflow	✅		127ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_eval_workflow	✅		3ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_fraction_workflow	✅		10ms
tests/explorer/workflow_test.py::WorkflowTest::test_math_workflow	✅		7ms
tests/explorer/workflow_test.py::WorkflowTest::test_rm_gallery_workflow	✅		132ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_0	✅		1ms
tests/explorer/workflow_test.py::WorkflowTest::test_workflow_repeatable_1	✅		100ms
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	✅		21.1s
tests/explorer/workflow_test.py::MultiTurnWorkflowTest_1::test_multi_turn_workflow	✅		20.9s
tests/explorer/workflow_test.py::TestWorkflowStateRecording::test_workflow_state_recording	✅		4.0s
tests/explorer/workflow_test.py::TestAgentScopeWorkflowAdapter::test_adapter	✅		703ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner	✅		154ms
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_runner_get_state	✅		8.0s
tests/explorer/workflow_test.py::TestWorkflowRunner::test_workflow_with_openai	✅		52.4s

Github Test Reporter by CTRF 💚