Skip to content

Add xattention test case#3676

Open
mangguo321 wants to merge 8 commits intoopenvinotoolkit:masterfrom
mangguo321:mang/add_xattention_test
Open

Add xattention test case#3676
mangguo321 wants to merge 8 commits intoopenvinotoolkit:masterfrom
mangguo321:mang/add_xattention_test

Conversation

@mangguo321
Copy link
Copy Markdown
Contributor

@mangguo321 mangguo321 commented Apr 10, 2026

Description

  1. Add xattention test case.
  2. Add get_scheduler_config() to expose the effective scheduler configuration, and assert xattention behavior in test when the configuration does not match expectations.

CVS-175120

Checklist:

  • This PR follows GenAI Contributing guidelines.
  • Tests have been updated or added to cover the new code.
  • This PR fully addresses the ticket.
  • I have made corresponding changes to the documentation.

Copilot AI review requested due to automatic review settings April 10, 2026 02:49
@github-actions github-actions Bot added category: GHA CI based on Github actions category: GGUF GGUF file reader labels Apr 10, 2026
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds a new Python E2E test to validate that enabling SparseAttentionMode.XATTENTION does not significantly degrade generation similarity versus the non-sparse baseline, and wires this test into the Linux CI matrix for continuous batching.

Changes:

  • Added test_xattention.py to compare similarity between xattention-enabled and disabled ContinuousBatchingPipeline runs.
  • Added a new Linux CI step to execute the xattention test under the continuous batching affected-components gate.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File Description
tests/python_tests/test_xattention.py New similarity-based regression test for XAttention vs baseline.
.github/workflows/linux.yml Runs the new xattention test as an additional Cacheopt E2E CI step.

Comment thread tests/python_tests/test_xattention.py Outdated
Comment thread .github/workflows/linux.yml Outdated
Copilot AI review requested due to automatic review settings April 10, 2026 05:53
@mangguo321 mangguo321 marked this pull request as ready for review April 10, 2026 05:54
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

Comment thread tests/python_tests/test_sparse_prefill.py
Comment thread tests/python_tests/test_sparse_prefill.py
Comment thread tests/python_tests/test_xattention.py Outdated
@Wovchena Wovchena requested a review from l-bat April 10, 2026 07:05
mangguo321 and others added 3 commits April 10, 2026 18:57
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Copilot AI review requested due to automatic review settings April 13, 2026 02:49
@github-actions github-actions Bot added category: continuous batching Continuous batching category: Python API Python API for GenAI category: CPP API Changes in GenAI C++ public headers labels Apr 13, 2026
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 9 out of 9 changed files in this pull request and generated 1 comment.

Comment thread src/cpp/src/continuous_batching/pipeline_base.hpp Outdated
Copilot AI review requested due to automatic review settings April 13, 2026 05:47
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 9 out of 9 changed files in this pull request and generated 1 comment.

Comment thread .github/workflows/linux.yml Outdated
Comment thread tests/python_tests/test_sparse_prefill.py
Comment thread tests/python_tests/test_xattention.py Outdated
Comment thread tests/python_tests/test_sparse_prefill.py
Comment thread src/cpp/src/continuous_batching/pipeline.cpp
mangguo321 and others added 2 commits April 13, 2026 19:24
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Comment thread .github/workflows/linux.yml Outdated
Comment thread .github/workflows/linux.yml Outdated
Comment thread tests/python_tests/test_sparse_prefill.py
Comment thread tests/python_tests/test_xattention.py Outdated
Copilot AI review requested due to automatic review settings April 14, 2026 05:40
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 11 out of 11 changed files in this pull request and generated 1 comment.

Comment thread src/cpp/include/openvino/genai/continuous_batching_pipeline.hpp
Copy link
Copy Markdown
Collaborator

@rkazants rkazants left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please provide proper PR description. The PR title does not reflect a real source changes. Here you seem to add get_schedule_config(). Please explain in the description why it is needed.

@mangguo321
Copy link
Copy Markdown
Contributor Author

Please provide proper PR description. The PR title does not reflect a real source changes. Here you seem to add get_schedule_config(). Please explain in the description why it is needed.

Updated the description. Thanks! @rkazants

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

category: continuous batching Continuous batching category: CPP API Changes in GenAI C++ public headers category: GGUF GGUF file reader category: GHA CI based on Github actions category: Python API Python API for GenAI

Projects

None yet

Development

Successfully merging this pull request may close these issues.

6 participants