Skip to content

[None][test] Increase timeout for Kimi-K2.5 disaggregated nvfp4 test#15970

Merged
Shixiaowei02 merged 1 commit into
NVIDIA:mainfrom
Shixiaowei02:fix/kimi-k25-disagg-timeout
Jul 6, 2026
Merged

[None][test] Increase timeout for Kimi-K2.5 disaggregated nvfp4 test#15970
Shixiaowei02 merged 1 commit into
NVIDIA:mainfrom
Shixiaowei02:fix/kimi-k25-disagg-timeout

Conversation

@Shixiaowei02

@Shixiaowei02 Shixiaowei02 commented Jul 6, 2026

Copy link
Copy Markdown
Collaborator

This pull request makes a minor update to the test configuration by increasing the timeout for a specific test case. The timeout for TestKimiK25::test_nvfp4 in accuracy/test_disaggregated_serving.py has been increased from 90 seconds to 180 seconds to accommodate longer test runtimes.

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.

Summary by CodeRabbit

  • Tests
    • Increased the timeout for one integration test in the Blackwell l0_dgx_b200 configuration, helping the test complete more reliably.

The test-list override TIMEOUT (90) capped TestKimiK25::test_nvfp4 at 90
minutes, overriding the class-level @pytest.mark.timeout(10800). Kimi-K2.5
(~1T-param NVFP4) is loaded across two disaggregated servers (ctx TP4 +
gen TP4); weight loading alone is ~37 min per server, so both servers only
reached startup-complete right as the 90-min budget expired, before the
GSM8K accuracy eval could run. Raise the override to 180 minutes to match
the class decorator and the gb200 Kimi entries.

Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
@Shixiaowei02 Shixiaowei02 force-pushed the fix/kimi-k25-disagg-timeout branch from 996283b to f5fad3c Compare July 6, 2026 09:16
@Shixiaowei02

Copy link
Copy Markdown
Collaborator Author

/bot skip --comment "timeout value modification only"

@coderabbitai

coderabbitai Bot commented Jul 6, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 7a608d3e-cff2-4773-97df-25090148c1d5

📥 Commits

Reviewing files that changed from the base of the PR and between 0044d5b and f5fad3c.

📒 Files selected for processing (1)
  • tests/integration/test_lists/test-db/l0_dgx_b200.yml

📝 Walkthrough

Walkthrough

Updates the timeout for the TestKimiK25::test_nvfp4 disaggregated serving test entry in the Blackwell l0_dgx_b200 test list from 90 to 180 seconds.

Changes

Test timeout update

Layer / File(s) Summary
Update test timeout value
tests/integration/test_lists/test-db/l0_dgx_b200.yml
Increased the timeout for TestKimiK25::test_nvfp4 from 90 to 180 seconds.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title matches the change and follows the required [None][type] summary format.
Description check ✅ Passed The description explains the change and includes the checklist, but the Test Coverage section is left blank.
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.

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57742 [ skip ] triggered by Bot. Commit: f5fad3c Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #57742 [ skip ] completed with state SUCCESS. Commit: f5fad3c
Skipping testing for commit f5fad3c

Link to invocation

@Shixiaowei02 Shixiaowei02 enabled auto-merge (squash) July 6, 2026 09:44
@Shixiaowei02 Shixiaowei02 merged commit 398e3e7 into NVIDIA:main Jul 6, 2026
13 of 14 checks passed
@Shixiaowei02 Shixiaowei02 deleted the fix/kimi-k25-disagg-timeout branch July 6, 2026 11:42
BrianLi23 pushed a commit to BrianLi23/TensorRT-LLM that referenced this pull request Jul 9, 2026
…VIDIA#15970)

Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
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.

3 participants