[https://nvbugs/5409414][fix] fix Not registered specs #6660

xinhe-nv · 2025-08-06T08:30:39Z

Summary by CodeRabbit

Tests
- Added new accuracy reference entries for the Llama-3.3-70B-Instruct model with FP8 quantization settings across multiple benchmarks.
- Removed skip entries for specific Llama-3.1-8B and Llama-3.3-70B FP8-related tests, enabling them to run as part of the test suite.
- Updated skip entries to reflect current bug tracking for select Llama-3.3-70B FP8 tests.
- Introduced memory-based test skipping for Llama-3.3-70B-Instruct tests requiring at least 80 GB of device memory.
- Improved server readiness checks by adding a timeout to prevent indefinite waiting during test setup.

Description

Test Coverage

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.

coderabbitai · 2025-08-06T08:30:46Z

📝 Walkthrough

Walkthrough

Additional entries specifying kv_cache_quant_algo: FP8 were added to the accuracy reference YAML files for the meta-llama/Llama-3.3-70B-Instruct model, duplicating existing quant_algo: FP8 entries. Three skip entries related to FP8 tests were removed from the test waive list, and one new skip entry was added referencing a different bug. Pytest markers were added to skip tests if device memory is insufficient. The infinite wait loop for disaggregated serving health was replaced with a time-bounded wait.

Changes

Cohort / File(s)	Change Summary
Accuracy Reference Updates `tests/integration/defs/accuracy/references/gpqa_diamond.yaml`, `tests/integration/defs/accuracy/references/gsm8k.yaml`, `tests/integration/defs/accuracy/references/mmlu.yaml`	Added duplicate accuracy entries for `meta-llama/Llama-3.3-70B-Instruct` with both `quant_algo: FP8` and `kv_cache_quant_algo: FP8`, matching existing accuracy values.
Test Waive List Cleanup and Update `tests/integration/test_lists/waives.txt`	Removed three skip entries related to FP8 tests referencing bug `https://nvbugs/5409414`. Added one new skip entry for `TestLlama3_3_70BInstruct::test_fp8_tp4` referencing bug `https://nvbugs/5440241`.
Test Class Pytest Marker Additions `tests/integration/defs/accuracy/test_cli_flow.py`, `tests/integration/defs/accuracy/test_llm_api_pytorch.py`	Added `@pytest.mark.skip_less_device_memory(80000)` decorator to `TestLlama3_3_70BInstruct` class to skip tests if device memory is below 80,000 MB.
Disaggregated Serving Health Check Timeout `tests/integration/defs/accuracy/test_disaggregated_serving.py`	Replaced infinite loop waiting for server health with a loop bounded by a 3600-second timeout, checking health endpoint once per second.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Possibly related PRs

test: add accuracy reference #6479: Adds or modifies accuracy reference entries by including the kv_cache_quant_algo field for Llama model configurations, directly related to updating accuracy test data.
test: skip llama3.3 70b test on cg4 #6293: Adds host and device memory skip markers to the TestLlama3_3_70BInstruct test class, related to test skipping conditions.
[TRTQA-2920][fix] Add failed cases into waives.txt #6581: Adds skip entries for some FP8 tests overlapping with the removed skip entries in this PR, indicating related test skip list management.

Suggested labels

Speculative Decoding, Disaggregated Serving, CI

Suggested reviewers

LarryXFly
crazydemo
yiqingy0

Note

⚡️ Unit Test Generation is now available in beta!

Learn more here, or try it out under "Finishing Touches" below.

📜 Recent review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 47ec440 and 608eb35.

📒 Files selected for processing (7)

tests/integration/defs/accuracy/references/gpqa_diamond.yaml (1 hunks)
tests/integration/defs/accuracy/references/gsm8k.yaml (1 hunks)
tests/integration/defs/accuracy/references/mmlu.yaml (1 hunks)
tests/integration/defs/accuracy/test_cli_flow.py (1 hunks)
tests/integration/defs/accuracy/test_disaggregated_serving.py (1 hunks)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1 hunks)
tests/integration/test_lists/waives.txt (1 hunks)

✅ Files skipped from review due to trivial changes (3)

tests/integration/defs/accuracy/references/gpqa_diamond.yaml
tests/integration/defs/accuracy/test_cli_flow.py
tests/integration/defs/accuracy/test_llm_api_pytorch.py

🚧 Files skipped from review as they are similar to previous changes (3)

tests/integration/defs/accuracy/references/mmlu.yaml
tests/integration/defs/accuracy/references/gsm8k.yaml
tests/integration/test_lists/waives.txt

🧰 Additional context used

📓 Path-based instructions (2)

**/*.py

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

**/*.py: Python code should conform to Python 3.8+.
Indent Python code with 4 spaces. Do not use tabs.
Always maintain the namespace when importing in Python, even if only one class or function from a module is used.
Python filenames should use snake_case (e.g., some_file.py).
Python classes should use PascalCase (e.g., class SomeClass).
Python functions and methods should use snake_case (e.g., def my_awesome_function():).
Python local variables should use snake_case. Prefix k for variable names that start with a number (e.g., k_99th_percentile).
Python global variables should use upper snake_case and prefix G (e.g., G_MY_GLOBAL).
Python constants should use upper snake_case (e.g., MY_CONSTANT).
Avoid shadowing variables declared in an outer scope in Python.
Initialize all externally visible members of a Python class in the constructor.
For interfaces that may be used outside a Python file, prefer docstrings over comments.
Comments in Python should be reserved for code within a function, or interfaces that are local to a file.
Use Google style docstrings for Python classes and functions, which can be parsed by Sphinx.
Attributes and variables in Python can be documented inline; attribute docstrings will be rendered under the class docstring.
Avoid using reflection in Python when functionality can be easily achieved without it.
When using try-except blocks in Python, limit the except to the smallest set of errors possible.
When using try-except blocks to handle multiple possible variable types in Python, keep the body of the try as small as possible, using the else block to implement the logic.

Files:

tests/integration/defs/accuracy/test_disaggregated_serving.py

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

📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)

All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the current year. This includes .cpp, .h, .cu, .py, and any other source files which are compiled or interpreted.

Files:

tests/integration/defs/accuracy/test_disaggregated_serving.py

🧠 Learnings (1)

📓 Common learnings

Learnt from: amitz-nv
PR: NVIDIA/TensorRT-LLM#5616
File: tensorrt_llm/executor/worker.py:375-384
Timestamp: 2025-07-17T09:01:27.402Z
Learning: In tensorrt_llm/executor/worker.py, the LoRA adapter cache optimization logic that checks `is_adapter_in_cpu_cache()` and conditionally passes None for weights/config has a known race condition issue that cannot be solved with simple error handling or verification checks. This is a known limitation that requires a more comprehensive solution.

⏰ 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)

tests/integration/defs/accuracy/test_disaggregated_serving.py (1)

149-150: LGTM! Excellent improvement to prevent indefinite test hangs.

Replacing the infinite loop with a time-bounded wait (3600 seconds) is a crucial improvement that prevents tests from hanging indefinitely if the disaggregated server fails to start. The timeout aligns with the --server_start_timeout parameter and still allows for early exit when the health endpoint responds successfully.

✨ Finishing Touches

📝 Generate Docstrings

🧪 Generate unit tests

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

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

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

Review comments: Directly reply to a review comment made by CodeRabbit. Example:
- I pushed a fix in commit <commit_id>, please review it.
- Explain this complex logic.
- Open a follow-up GitHub issue for this discussion.
Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
- @coderabbitai explain this code block.
PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
- @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
- @coderabbitai read src/utils.ts and explain its main purpose.
- @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR comments)

@coderabbitai pause to pause the reviews on a PR.
@coderabbitai resume to resume the paused reviews.
@coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
@coderabbitai full review to do a full review from scratch and review all the files again.
@coderabbitai summary to regenerate the summary of the PR.
@coderabbitai generate docstrings to generate docstrings for this PR.
@coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
@coderabbitai generate unit tests to generate unit tests for this PR.
@coderabbitai resolve resolve all the CodeRabbit review comments.
@coderabbitai configuration to show the current CodeRabbit configuration for the repository.
@coderabbitai help to get help.

Other keywords and placeholders

Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
Add @coderabbitai or @coderabbitai title anywhere in the PR title to generate the title automatically.

Documentation and Community

Visit our Documentation for detailed information on how to use CodeRabbit.
Join our Discord Community to get help, request features, and share feedback.
Follow us on X/Twitter for updates and announcements.

xinhe-nv · 2025-08-06T09:16:23Z

/bot run

tensorrt-cicd · 2025-08-06T09:22:36Z

PR_Github #14289 [ run ] triggered by Bot

tensorrt-cicd · 2025-08-06T14:39:29Z

PR_Github #14289 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #10793 completed with status: 'FAILURE'

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

xinhe-nv · 2025-08-07T03:25:03Z

/bot run

tensorrt-cicd · 2025-08-07T03:30:48Z

PR_Github #14369 [ run ] triggered by Bot

tensorrt-cicd · 2025-08-07T05:09:43Z

PR_Github #14369 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #10860 completed with status: 'FAILURE'

xinhe-nv · 2025-08-07T06:00:09Z

/bot run

tensorrt-cicd · 2025-08-07T06:05:14Z

PR_Github #14396 [ run ] triggered by Bot

tensorrt-cicd · 2025-08-07T07:22:07Z

PR_Github #14396 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #10882 completed with status: 'FAILURE'

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com> Co-authored-by: Larry <197874197+LarryXFly@users.noreply.github.com>

xinhe-nv force-pushed the user/xinhe/fix branch 2 times, most recently from f9f7992 to 1112768 Compare August 6, 2025 08:59

xinhe-nv changed the title ~~[None][fix] fix Not registered specs~~ [https://nvbugs/5409414][fix] fix Not registered specs Aug 6, 2025

xinhe-nv requested review from LarryXFly, crazydemo and syuoni August 6, 2025 09:15

xinhe-nv marked this pull request as ready for review August 6, 2025 09:16

xinhe-nv force-pushed the user/xinhe/fix branch from 1112768 to c484d11 Compare August 6, 2025 09:16

xinhe-nv enabled auto-merge (squash) August 6, 2025 09:16

crazydemo approved these changes Aug 6, 2025

View reviewed changes

xinhe-nv force-pushed the user/xinhe/fix branch from c484d11 to 47ec440 Compare August 6, 2025 10:23

xinhe-nv force-pushed the user/xinhe/fix branch from 47ec440 to 40c80a6 Compare August 7, 2025 03:13

unwaive tests

608eb35

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

xinhe-nv force-pushed the user/xinhe/fix branch from 40c80a6 to 608eb35 Compare August 7, 2025 03:17

Merge branch 'main' into user/xinhe/fix

38e407c

LarryXFly approved these changes Aug 7, 2025

View reviewed changes

Merge branch 'main' into user/xinhe/fix

f47a523

LarryXFly disabled auto-merge August 7, 2025 07:55

LarryXFly merged commit 0a467b0 into NVIDIA:main Aug 7, 2025
3 checks passed

xinhe-nv deleted the user/xinhe/fix branch August 7, 2025 08:08

coderabbitai bot mentioned this pull request Aug 12, 2025

[TRTLLM-7014][chore] Add accuracy test for ctx and gen workers with different models #6741

Merged

tongyuantongyu mentioned this pull request Aug 14, 2025

[None][chore] Mass integration of release/1.0 #6864

Merged

coderabbitai bot mentioned this pull request Aug 26, 2025

[https://nvbugs/5478151][fix] Add missing spec for Llama-3.3 70B #7267

Merged

[https://nvbugs/5409414][fix] fix Not registered specs #6660

[https://nvbugs/5409414][fix] fix Not registered specs #6660

Uh oh!

Conversation

xinhe-nv commented Aug 6, 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

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

coderabbitai bot commented Aug 6, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested labels

Suggested reviewers

Chat

Support

CodeRabbit Commands (Invoked using PR comments)

Other keywords and placeholders

Documentation and Community

Uh oh!

xinhe-nv commented Aug 6, 2025

Uh oh!

tensorrt-cicd commented Aug 6, 2025

Uh oh!

tensorrt-cicd commented Aug 6, 2025

Uh oh!

xinhe-nv commented Aug 7, 2025

Uh oh!

tensorrt-cicd commented Aug 7, 2025

Uh oh!

tensorrt-cicd commented Aug 7, 2025

Uh oh!

xinhe-nv commented Aug 7, 2025

Uh oh!

tensorrt-cicd commented Aug 7, 2025

Uh oh!

tensorrt-cicd commented Aug 7, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

xinhe-nv commented Aug 6, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Aug 6, 2025 •

edited

Loading