Skip to content

[None][fix] api stability bug in status label - #7861

Merged
Superjomn merged 1 commit into
NVIDIA:release/1.0from
Superjomn:doc.change-knob-status
Sep 22, 2025
Merged

[None][fix] api stability bug in status label#7861
Superjomn merged 1 commit into
NVIDIA:release/1.0from
Superjomn:doc.change-knob-status

Conversation

@Superjomn

@Superjomn Superjomn commented Sep 19, 2025

Copy link
Copy Markdown
Collaborator

Summary by CodeRabbit

  • New Features

    • None.
  • Documentation

    • The “fail fast when attention window is too large” option is now labeled as Prototype in generated API metadata and docs.
  • Tests

    • API stability checks updated to validate constructor parameter status so parameter-level Prototype markers are surfaced.
  • Chores

    • Metadata enhancements to better reflect feature maturity in schemas and documentation outputs.

Description

Fix the bug that the non-committed argument, missing "status" can pass the api_stability test.

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.

@Superjomn
Superjomn requested a review from a team as a code owner September 19, 2025 06:05
@coderabbitai

coderabbitai Bot commented Sep 19, 2025

Copy link
Copy Markdown
Contributor

Warning

Rate limit exceeded

@Superjomn has exceeded the limit for the number of commits or files that can be reviewed per hour. Please wait 2 minutes and 45 seconds before requesting another review.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

📥 Commits

Reviewing files that changed from the base of the PR and between d8b6a0b and 00cf3ed.

📒 Files selected for processing (2)
  • tensorrt_llm/llmapi/llm_args.py (1 hunks)
  • tests/unittest/api_stability/api_stability_core.py (1 hunks)
📝 Walkthrough

Walkthrough

Adds a status="prototype" metadata to one Field in BaseLlmArgs and updates the API stability test harness to treat committed __init__ specially: skip method-level status checks but still validate its parameter statuses; other committed methods remain fully skipped.

Changes

Cohort / File(s) Summary of Changes
LLM args status metadata
tensorrt_llm/llmapi/llm_args.py
fail_fast_on_attention_window_too_large Field in BaseLlmArgs now includes status="prototype" in its Field declaration, adding that key to the field's schema metadata; no runtime behavior changes.
API stability test harness
tests/unittest/api_stability/api_stability_core.py
ApiStabilityTestHarness.check_status logic adjusted: when a method is in committed_data and is __init__, the harness skips the method-level status check but continues to validate __init__ parameter statuses; non-__init__ committed methods are still fully skipped.

Sequence Diagram(s)

sequenceDiagram
  participant Runner as Test Runner
  participant Harness as ApiStabilityTestHarness
  participant Committed as committed_data

  Runner->>Harness: run check_status()
  loop per method
    Harness->>Committed: is method in committed_data?
    alt not committed
      Harness->>Harness: perform method-level status checks
      Harness->>Harness: validate parameter statuses
    else committed and method == "__init__"
      note right of Harness: skip method-level status check
      Harness->>Harness: validate __init__ parameter statuses
    else committed and method != "__init__"
      note right of Harness: skip entire method
    end
  end
  Harness-->>Runner: return results
Loading

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Pre-merge checks and finishing touches

❌ Failed checks (1 inconclusive)
Check name Status Explanation Resolution
Description Check ❓ Inconclusive The PR description includes the repository template and a concise Description stating the bug fixed (non-committed argument missing "status" passing api_stability), but the Test Coverage section is empty and the description omits concrete implementation details, specific tests added or updated, and validation steps, so it is incomplete for a full review. Please fill the Test Coverage section with the relevant unit/integration tests (or state none were added), add a brief implementation summary listing the key changed files and behavioral impact, and include verification steps or CI results that demonstrate the fix; once those details are provided the description check can be marked as pass.
✅ Passed checks (2 passed)
Check name Status Explanation
Title Check ✅ Passed The title "[None][fix] api stability bug in status label" succinctly and correctly summarizes the primary change — a fix to API stability/status labeling — and follows the repository's bracketed title template, so it is clear and relevant for reviewers.
Docstring Coverage ✅ Passed Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

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.

@Superjomn

Copy link
Copy Markdown
Collaborator Author

/bot run

@Superjomn Superjomn changed the title [None][doc] fix api stability bug in status label [None][fix] api stability bug in status label Sep 19, 2025
@nv-guomingz nv-guomingz added the Release Blocker PRs that blocking the final release build or branching out the release branch label Sep 19, 2025

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Actionable comments posted: 0

🧹 Nitpick comments (4)
tests/unittest/api_stability/api_stability_core.py (3)

469-470: Guard committed reference being None and avoid unnecessary getattr.

Prevent AttributeError when committed references are absent and move getattr after the skip check. Also clarify the nearby comment.

Apply:

-        committed_data = self.reference_committed.to_dict()
+        committed_data = (self.reference_committed.to_dict()
+                          if self.reference_committed is not None else None)
@@
-            # step 1: check the method status
-            method = getattr(self.TEST_CLASS, method_name)
-            if method_name in committed_data.get('methods', {}):
-                if method_name != "__init__":
-                    continue
-                # Both committed and non-committed methods have __init__ with different parameters
+            # step 1: check the method status
+            committed_methods = committed_data.get('methods', {}) if committed_data else {}
+            if method_name in committed_methods and method_name != "__init__":
+                continue
+            # Both committed and non-committed snapshots may include __init__ with different parameters
+            method = getattr(self.TEST_CLASS, method_name)

Also applies to: 506-516


534-534: Remove noisy debug print from test harness.

This pollutes test output.

-                    print(f"param_name: {param_name}, param_data: {param_data}")

1-1: Add NVIDIA Apache-2.0 header.

Required by repo guidelines.

+# Copyright (c) 2025, NVIDIA CORPORATION.
+# Licensed under the Apache License, Version 2.0 (the "License");
+# http://www.apache.org/licenses/LICENSE-2.0
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
tensorrt_llm/llmapi/llm_args.py (1)

1-1: Add NVIDIA Apache-2.0 header.

Required by repo guidelines.

+# Copyright (c) 2025, NVIDIA CORPORATION.
+# Licensed under the Apache License, Version 2.0 (the "License");
+# http://www.apache.org/licenses/LICENSE-2.0
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
📜 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 1240724 and b7ccd8b.

📒 Files selected for processing (2)
  • tensorrt_llm/llmapi/llm_args.py (1 hunks)
  • tests/unittest/api_stability/api_stability_core.py (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:

  • tensorrt_llm/llmapi/llm_args.py
  • tests/unittest/api_stability/api_stability_core.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:

  • tensorrt_llm/llmapi/llm_args.py
  • tests/unittest/api_stability/api_stability_core.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:

  • tensorrt_llm/llmapi/llm_args.py
  • tests/unittest/api_stability/api_stability_core.py
🧠 Learnings (1)
📓 Common learnings
Learnt from: venkywonka
PR: NVIDIA/TensorRT-LLM#6029
File: .github/pull_request_template.md:45-53
Timestamp: 2025-08-27T17:50:13.264Z
Learning: For PR templates in TensorRT-LLM, avoid suggesting changes that would increase developer overhead, such as converting plain bullets to mandatory checkboxes. The team prefers guidance-style bullets that don't require explicit interaction to reduce friction in the PR creation process.
⏰ 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 (1)
tensorrt_llm/llmapi/llm_args.py (1)

1183-1188: Status marker on fail_fast_on_attention_window_too_large is correct.

This wires the knob into json_schema_extra for status checks.

Please confirm llm.yaml reflects status: "prototype" for this field so ApiStabilityTestHarness passes.

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #19296 [ run ] triggered by Bot

@Superjomn
Superjomn enabled auto-merge (squash) September 19, 2025 06:30
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #19296 [ run ] completed with state SUCCESS
/LLM/release-1.0/L0_MergeRequest_PR pipeline #422 completed with status: 'FAILURE'

@Superjomn
Superjomn force-pushed the doc.change-knob-status branch from b7ccd8b to d8b6a0b Compare September 20, 2025 10:38
@Superjomn

Copy link
Copy Markdown
Collaborator Author

/bot run

@github-actions

Copy link
Copy Markdown

👎 Promotion blocked, new vulnerability found

Vulnerability report

Component Vulnerability Description Severity
pytorch CVE-2025-3730 A vulnerability, which was classified as problematic, was found in PyTorch 2.6.0. Affected is the function torch.nn.functional.ctc_loss of the file aten/src/ATen/native/LossCTC.cpp. The manipulation leads to denial of service. An attack has to be approached locally. The exploit has been disclosed to the public and may be used. The real existence of this vulnerability is still doubted at the moment. The name of the patch is 46fc5d8e360127361211cb237d5f9eef0223e567. It is recommended to apply a patch to fix this issue. The security policy of the project warns to use unknown models which might establish malicious effects. MEDIUM

@Superjomn

Copy link
Copy Markdown
Collaborator Author

/bot run

@github-actions

Copy link
Copy Markdown

👎 Promotion blocked, new vulnerability found

Vulnerability report

Component Vulnerability Description Severity
pytorch CVE-2025-3730 A vulnerability, which was classified as problematic, was found in PyTorch 2.6.0. Affected is the function torch.nn.functional.ctc_loss of the file aten/src/ATen/native/LossCTC.cpp. The manipulation leads to denial of service. An attack has to be approached locally. The exploit has been disclosed to the public and may be used. The real existence of this vulnerability is still doubted at the moment. The name of the patch is 46fc5d8e360127361211cb237d5f9eef0223e567. It is recommended to apply a patch to fix this issue. The security policy of the project warns to use unknown models which might establish malicious effects. MEDIUM

@Superjomn

Copy link
Copy Markdown
Collaborator Author

/bot run --stage-list "A10-Build_Docs"

@github-actions

Copy link
Copy Markdown

👎 Promotion blocked, new vulnerability found

Vulnerability report

Component Vulnerability Description Severity
pytorch CVE-2025-3730 A vulnerability, which was classified as problematic, was found in PyTorch 2.6.0. Affected is the function torch.nn.functional.ctc_loss of the file aten/src/ATen/native/LossCTC.cpp. The manipulation leads to denial of service. An attack has to be approached locally. The exploit has been disclosed to the public and may be used. The real existence of this vulnerability is still doubted at the moment. The name of the patch is 46fc5d8e360127361211cb237d5f9eef0223e567. It is recommended to apply a patch to fix this issue. The security policy of the project warns to use unknown models which might establish malicious effects. MEDIUM

Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
@Superjomn
Superjomn force-pushed the doc.change-knob-status branch from d8b6a0b to 00cf3ed Compare September 22, 2025 03:10
@Superjomn

Copy link
Copy Markdown
Collaborator Author

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #19482 [ run ] triggered by Bot

@Superjomn

Copy link
Copy Markdown
Collaborator Author

/bot skip --comment "generic doc related change, and passed x86 single gpu, no need to run multi-gpu"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #19511 [ skip ] triggered by Bot

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #19482 [ run ] completed with state ABORTED
LLM/release-1.0/L0_MergeRequest_PR #432 (Blue Ocean) completed with status: ABORTED

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #19511 [ skip ] completed with state SUCCESS
Skipping testing for commit 00cf3ed

@Superjomn
Superjomn merged commit ce6ebf6 into NVIDIA:release/1.0 Sep 22, 2025
4 checks passed
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 23, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 23, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 23, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
yuanjingx87 pushed a commit that referenced this pull request Sep 23, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 24, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 24, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 24, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 24, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 24, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 24, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 24, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 25, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
chzblych pushed a commit that referenced this pull request Sep 25, 2025
Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Release Blocker PRs that blocking the final release build or branching out the release branch

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants