Skip to content

[https://nvbugs/6274934][fix] Skip DeepSeek-V3-Lite dis-agg test on non-Hopper#15577

Closed
Shixiaowei02 wants to merge 1 commit into
NVIDIA:mainfrom
Shixiaowei02:user/xiaoweis/nvbug-6274934-skip-no-hopper
Closed

[https://nvbugs/6274934][fix] Skip DeepSeek-V3-Lite dis-agg test on non-Hopper#15577
Shixiaowei02 wants to merge 1 commit into
NVIDIA:mainfrom
Shixiaowei02:user/xiaoweis/nvbug-6274934-skip-no-hopper

Conversation

@Shixiaowei02

@Shixiaowei02 Shixiaowei02 commented Jun 24, 2026

Copy link
Copy Markdown
Collaborator

Summary by CodeRabbit

  • Tests
    • Updated one conditional disaggregation worker test to skip on systems without Hopper support, reducing unsupported test runs and related failures.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

  • PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

  • PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

  • Test cases are provided for new code paths (see test instructions)

  • If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

  • Any new dependencies have been scanned for license and vulnerabilities

  • CODEOWNERS updated if ownership changes

  • Documentation updated as needed

  • Update tava architecture diagram if there is a significant design change in PR.

  • The reviewers assigned automatically/manually are appropriate for the PR.

  • Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

@Shixiaowei02
Shixiaowei02 requested a review from a team as a code owner June 24, 2026 06:57
@Shixiaowei02
Shixiaowei02 force-pushed the user/xiaoweis/nvbug-6274934-skip-no-hopper branch from e6c42c1 to d3d6119 Compare June 24, 2026 06:57
@Shixiaowei02

Copy link
Copy Markdown
Collaborator Author

/bot run --add-multi-gpu-test --disable-fail-fast

@coderabbitai

coderabbitai Bot commented Jun 24, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

📝 Walkthrough

Walkthrough

The @skip_no_hopper decorator is added to the test_workers_conditional_disaggregation_deepseek_v3_lite_bf16 test in the disaggregated workers integration test file, gating its execution to environments with Hopper hardware support. No other logic is changed.

Changes

Test Hardware Gate

Layer / File(s) Summary
Add @skip_no_hopper to DeepSeek-V3-Lite bf16 test
tests/integration/defs/disaggregated/test_workers.py
Adds @skip_no_hopper decorator to test_workers_conditional_disaggregation_deepseek_v3_lite_bf16, skipping execution on non-Hopper environments.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Suggested reviewers

  • xinhe-nv
🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The PR description is still the template placeholder and does not explain the issue, solution, or test coverage. Add a short Description and Test Coverage section that summarizes the Hopper-only skip and the tests used to validate it.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly matches the change: skipping the DeepSeek-V3-Lite disaggregation test on non-Hopper GPUs.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Comment @coderabbitai help to get the list of available commands.

@Shixiaowei02

Copy link
Copy Markdown
Collaborator Author

/bot run --add-multi-gpu-test --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55642 [ run ] triggered by Bot. Commit: d3d6119 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55642 [ run ] completed with state FAILURE. Commit: d3d6119

Link to invocation

@fredricz-20070104 fredricz-20070104 left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Approved

@Shixiaowei02
Shixiaowei02 force-pushed the user/xiaoweis/nvbug-6274934-skip-no-hopper branch from d3d6119 to a9454a5 Compare June 30, 2026 02:10
@Shixiaowei02

Copy link
Copy Markdown
Collaborator Author

/bot run --add-multi-gpu-test --disable-fail-fast

@Shixiaowei02
Shixiaowei02 force-pushed the user/xiaoweis/nvbug-6274934-skip-no-hopper branch from a9454a5 to c56defe Compare July 1, 2026 06:52
@Shixiaowei02

Copy link
Copy Markdown
Collaborator Author

/bot run --add-multi-gpu-test --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #56871 [ run ] triggered by Bot. Commit: c56defe Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #56871 [ run ] completed with state SUCCESS. Commit: c56defe
/LLM/main/L0_MergeRequest_PR pipeline #45682 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

  • Please check the failed tests and fix your PR
  • If you cannot view the failures, ask the CI triggerer to share details
  • Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

…disagg worker test on non-Hopper

test_workers_conditional_disaggregation_deepseek_v3_lite_bf16 runs DeepSeek-V3-Lite, which uses MLA. The context-phase MLA FMHA kernels (headSize=192, headSizeV=128) are only available on Hopper (SM90), so on pre-Hopper GPUs AttentionOp::initialize() aborts with "Deepseek should be supported by fmha in context part."

Add @skip_no_hopper, matching the sibling DeepSeek-V3-Lite disaggregation tests (test_workers_kv_cache_aware_router_deepseek_v3_lite_bf16 and test_disaggregated_deepseek_v3_lite_bf16_conditional).

Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
@Shixiaowei02
Shixiaowei02 force-pushed the user/xiaoweis/nvbug-6274934-skip-no-hopper branch from c56defe to d554c77 Compare July 15, 2026 10:53
@Shixiaowei02
Shixiaowei02 requested review from a team as code owners July 15, 2026 10:53
@Shixiaowei02

Copy link
Copy Markdown
Collaborator Author

/bot run --stage-list "DGX_H100-4_GPUs-PyTorch-DeepSeek-1"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59443 [ run ] triggered by Bot. Commit: d554c77 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #59443 [ run ] completed with state FAILURE. Commit: d554c77
/LLM/main/L0_MergeRequest_PR pipeline #47911 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

  • Please check the failed tests and fix your PR
  • If you cannot view the failures, ask the CI triggerer to share details
  • Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

@yufeiwu-nv
yufeiwu-nv removed the request for review from ruodil July 16, 2026 06:53
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.

4 participants