Skip to content

Implement integration tests in CI pipeline (won't be merged)#532

Closed
meiyeh123 wants to merge 38 commits intomainfrom
sting_test
Closed

Implement integration tests in CI pipeline (won't be merged)#532
meiyeh123 wants to merge 38 commits intomainfrom
sting_test

Conversation

@meiyeh123
Copy link
Collaborator

@meiyeh123 meiyeh123 commented Aug 21, 2025

Description

Based on the Integration Test requirements, this change adds a new test accuracy on TPU to the CI pipeline. The test covers the Llama-3.1-8B-Instruct and Llama-3.1-70B-Instruct models, modifying the test to support comparing EXPECTED_VALUE. It also allows users to input tensor-parallel-size and model-names parameters for greater flexibility during execution.

Based on the description of the vllm PR at vllm-project/vllm#18800, we have changed the lm_eval version used to git+https://github.com/EleutherAI/lm-evaluation-harness.git@206b7722158f58c35b7ffcd53b035fdbdda5126d#egg=lm-eval[api].

In the future, we'll support collecting expected values on GPUs and comparing them with results from TPUs. We'll achieve this by enabling both GPUs and TPUs to read and write expected JSON files between Buildkite steps. We've already started implementing some of these files.

The testing logic is based on the source code at https://github.com/vllm-project/vllm/blob/839ab00/tests/entrypoints/llm/test_accuracy.py. We are developing based on this source.

Tests

Tested on the Buildkite agent.

Checklist

Before submitting this PR, please make sure:

  • I have performed a self-review of my code.
  • I have necessary comments in my code, particularly in hard-to-understand areas.

@github-actions
Copy link

Description

Start with a short description of what the PR does and how this is a change from
the past.

The rest of the description includes relevant details and context, examples:

  • why is this change being made,
  • the problem being solved and any relevant context,
  • why this is a good solution,
  • some information about the specific implementation,
  • shortcomings of the solution and possible future improvements.

If the change fixes a bug or a Github issue, please include a link, e.g.,:
FIXES: b/123456
FIXES: #123456

Tests

Please describe how you tested this change, and include any instructions and/or
commands to reproduce.

Checklist

Before submitting this PR, please make sure:

  • I have performed a self-review of my code.
  • I have necessary comments in my code, particularly in hard-to-understand areas.
  • I have made or will make corresponding changes to any relevant documentation.

@CienetStingLin CienetStingLin force-pushed the sting_test branch 4 times, most recently from 0e2c5af to f643160 Compare September 4, 2025 03:35
@CienetStingLin CienetStingLin changed the title Testing CI script, won't be merged (intergration test ) Implement integration tests in CI pipeline (won't be merged) Sep 4, 2025
…y on TPU to the CI pipeline. The test covers the Llama-3.1-8B-Instruct and Llama-3.1-70B-Instruct models, modifying the test to support comparing `EXPECTED_VALUE`. It also allows users to input `tensor-parallel-size` and `model-names` parameters for greater flexibility during execution
@meiyeh123
Copy link
Collaborator Author

this PR is deprecated

@meiyeh123 meiyeh123 closed this Oct 16, 2025
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