[TRTLLM-8366][feat] add kimi multi nodes case #8025

xinhe-nv · 2025-09-26T10:14:53Z

Summary by CodeRabbit

Tests
- Expanded multi-node evaluation suite to include an additional model configuration.
- Increased timeout for a long-running multi-node scenario to improve stability.
- Updated test lists to reflect the new coverage.
- Added waivers to skip a specific multi-node evaluation in certain environments to reduce noise.

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)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
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

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

Details

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

xinhe-nv · 2025-10-14T01:49:33Z

/bot run --skip-test

coderabbitai · 2025-10-14T01:54:04Z

📝 Walkthrough

Walkthrough

Increases a test timeout from 5400 to 7200 seconds, adds a new model parameter ('Kimi-K2-Instruct') with skip markers to a multi-node evaluation test, updates the QA test list to include the new parametrized case, and adds corresponding waiver entries to skip that case.

Changes

Cohort / File(s)	Summary of changes
Integration E2E tests `tests/integration/defs/test_e2e.py`	Increased timeout for `test_ptp_quickstart_advanced_llama_multi_nodes` to 7200s; added `pytest.param('Kimi-K2-Instruct', marks=(skip_pre_hopper, skip_post_blackwell))` to `test_multi_nodes_eval` parameterization.
QA test list `tests/integration/test_lists/qa/llm_function_multinode.txt`	Added `test_multi_nodes_eval[Kimi-K2-Instruct-tp16-mmlu]` to multi-node evaluation list.
Waivers `tests/integration/test_lists/waives.txt`	Added waiver entries to skip `test_e2e.py::test_multi_nodes_eval[Kimi-K2-Instruct-tp16-mmlu]` (marked SKIP).

Sequence Diagram(s)

sequenceDiagram
  autonumber
  actor Dev as Developer
  participant Py as pytest Runner
  participant T as test_e2e::test_multi_nodes_eval
  participant WL as Waivers List
  note over Py: Test discovery & param collection

  Dev->>Py: Run test suite
  Py->>T: Collect params (… existing, 'Kimi-K2-Instruct')
  note right of T: Param has marks: skip_pre_hopper, skip_post_blackwell

  Py->>WL: Check waivers
  alt Waiver matches
    WL-->>Py: SKIP
    Py-->>Dev: Report skipped case (Kimi-K2-Instruct-tp16-mmlu)
  else No waiver
    alt Env triggers skip mark
      T-->>Py: Skip due to marker
      Py-->>Dev: Report skipped
    else Not skipped
      T->>Py: Execute multi-node eval (tp16, mmlu)
      Py-->>Dev: Report result
    end
  end

  note over Py: Separate test: timeout increased to 7200s for advanced llama multi-nodes

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Pre-merge checks and finishing touches

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description Check	⚠️ Warning	The PR description consists solely of the unused template and placeholder comments without any actual summary, description of the change, or test coverage details, so it does not meet the requirement to explain what was done and why.	Please fill in the template sections with a concise summary of the change, a description of the implementation and rationale, and a list of relevant tests to ensure adequate coverage.
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	You can run `@coderabbitai generate docstrings` to improve docstring coverage.

✅ Passed checks (1 passed)

Check name	Status	Explanation
Title Check	✅ Passed	The title correctly follows the repository’s “[JIRA ticket][type] Summary” format and concisely describes the main change of adding a Kimi multi-node test case, making it clear to reviewers at a glance.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment

📜 Recent review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 9bc055f and 154440d.

📒 Files selected for processing (3)

tests/integration/defs/test_e2e.py (2 hunks)
tests/integration/test_lists/qa/llm_function_multinode.txt (1 hunks)
tests/integration/test_lists/waives.txt (1 hunks)

🧰 Additional context used

📓 Path-based instructions (3)

**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Use only spaces, no tabs; indent with 4 spaces.

Files:

tests/integration/defs/test_e2e.py

**/*.py

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.

Files:

tests/integration/defs/test_e2e.py

**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).

Files:

tests/integration/defs/test_e2e.py

🧠 Learnings (1)

📚 Learning: 2025-09-17T02:48:52.732Z

Learnt from: tongyuantongyu
PR: NVIDIA/TensorRT-LLM#7781
File: tests/integration/test_lists/waives.txt:313-313
Timestamp: 2025-09-17T02:48:52.732Z
Learning: In TensorRT-LLM, `tests/integration/test_lists/waives.txt` is specifically for waiving/skipping tests, while other test list files like those in `test-db/` and `qa/` directories are for different test execution contexts (pre-merge, post-merge, QA tests). The same test appearing in both waives.txt and execution list files is intentional - the test is part of test suites but will be skipped due to the waiver.

Applied to files:

tests/integration/test_lists/waives.txt

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

GitHub Check: Pre-commit Check

🔇 Additional comments (4)

tests/integration/test_lists/qa/llm_function_multinode.txt (1)

10-10: LGTM! New test case follows the established pattern.

The addition of the Kimi-K2-Instruct multi-node evaluation test is consistent with the existing test list format and properly coordinated with the corresponding changes in test_e2e.py and waives.txt.

tests/integration/test_lists/waives.txt (1)

365-365: LGTM! Waiver entry properly formatted.

The waiver follows the correct pattern for this file, includes a bug reference for tracking, and is intentionally paired with the test list entry per the repository's conventions.

Based on learnings.

tests/integration/defs/test_e2e.py (2)

3362-3362: Verify the timeout increase is necessary.

The timeout is increased by 33% (from 90 to 120 minutes) for multi-node evaluation tests. While this may be justified for the Kimi-K2-Instruct model or to provide more margin for all multi-node tests, please confirm:

Is this increase specifically required for Kimi-K2-Instruct, or is it a general improvement for all parameterized models in this test?

Has test execution data shown that 5400 seconds is insufficient?

If this is specifically for Kimi-K2-Instruct and the test is currently waived (per waives.txt), consider whether the timeout increase should wait until the test is actually enabled.

3379-3380: Verify the model path pattern.

The model path 'Kimi-K2-Instruct' appears to be a simple name without a subdirectory, which differs from most other entries in this test that use full paths like 'llama-3.3-models/Llama-3.3-70B-Instruct' or 'Qwen3/Qwen3-235B-A22B'.

Please confirm:

Is 'Kimi-K2-Instruct' located directly at {llm_models_root()}/Kimi-K2-Instruct?

Is this path consistent with how the model will be stored in the test environment?

The skip markers (skip_pre_hopper, skip_post_blackwell) appropriately restrict this test to Hopper and Blackwell architectures, which is reasonable for a new large model.

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

tensorrt-cicd · 2025-10-14T01:57:33Z

PR_Github #21277 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-14T03:43:43Z

PR_Github #21277 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #16065 (Partly Tested) completed with status: 'SUCCESS'

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>

xinhe-nv · 2025-10-14T03:52:10Z

/bot reuse-pipeline

tensorrt-cicd · 2025-10-14T03:57:52Z

PR_Github #21296 [ reuse-pipeline ] triggered by Bot

tensorrt-cicd · 2025-10-14T04:35:47Z

PR_Github #21296 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #21277 (Partly Tested) for commit 70e4c61

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com> Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>

xinhe-nv force-pushed the kimi branch 3 times, most recently from 7b20add to 288859f Compare September 29, 2025 06:37

xinhe-nv force-pushed the kimi branch 3 times, most recently from 4931865 to 154440d Compare October 14, 2025 01:45

xinhe-nv changed the title ~~[None][chore] draft kimi tool calling tests~~ [TRTLLM-8366][feat] add kimi multi nodes case Oct 14, 2025

xinhe-nv requested review from LarryXFly, StanleySun639 and crazydemo October 14, 2025 01:47

xinhe-nv marked this pull request as ready for review October 14, 2025 01:49

xinhe-nv enabled auto-merge (squash) October 14, 2025 01:49

xinhe-nv requested review from Shixiaowei02 and jieli-matrix October 14, 2025 01:49

LarryXFly approved these changes Oct 14, 2025

View reviewed changes

add kimi multi nodes tests

70e4c61

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>

xinhe-nv force-pushed the kimi branch from 154440d to 70e4c61 Compare October 14, 2025 03:51

xinhe-nv merged commit 371fcb0 into NVIDIA:main Oct 14, 2025
5 checks passed

xinhe-nv deleted the kimi branch October 14, 2025 05:15

govind-ramnarayan pushed a commit to nv-auto-deploy/TensorRT-LLM that referenced this pull request Oct 21, 2025

[TRTLLM-8366][feat] add kimi multi nodes case (NVIDIA#8025)

c698ec1

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 1, 2025

[TRTLLM-8366][feat] add kimi multi nodes case (NVIDIA#8025)

32decf0

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025

[TRTLLM-8366][feat] add kimi multi nodes case (NVIDIA#8025)

87882cf

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025

[TRTLLM-8366][feat] add kimi multi nodes case (NVIDIA#8025)

02b212d

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025

[TRTLLM-8366][feat] add kimi multi nodes case (NVIDIA#8025)

5e72651

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[TRTLLM-8366][feat] add kimi multi nodes case #8025

[TRTLLM-8366][feat] add kimi multi nodes case #8025

Uh oh!

xinhe-nv commented Sep 26, 2025 •

edited by coderabbitai bot

Loading

Uh oh!

xinhe-nv commented Oct 14, 2025

Uh oh!

coderabbitai bot commented Oct 14, 2025

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

xinhe-nv commented Oct 14, 2025

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

[TRTLLM-8366][feat] add kimi multi nodes case #8025

[TRTLLM-8366][feat] add kimi multi nodes case #8025

Uh oh!

Conversation

xinhe-nv commented Sep 26, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Description

Test Coverage

PR Checklist

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

xinhe-nv commented Oct 14, 2025

Uh oh!

coderabbitai bot commented Oct 14, 2025

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Pre-merge checks and finishing touches

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

xinhe-nv commented Oct 14, 2025

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

xinhe-nv commented Sep 26, 2025 •

edited by coderabbitai bot

Loading