[None][test] Add accuracy test for Qwen3Next model #8111
Conversation
|
/bot run --stage-name "DGX_H100-4_GPUs-PyTorch-Qwen3Next-1" |
|
PR_Github #20453 Bot args parsing error: usage: /bot [-h] |
|
/bot run --stage-list "DGX_H100-4_GPUs-PyTorch-Qwen3Next-1" |
|
PR_Github #20455 [ run ] triggered by Bot |
|
PR_Github #20455 [ run ] completed with state |
|
/bot run --stage-list "DGX_H100-4_GPUs-PyTorch-Qwen3Next-1" |
|
PR_Github #20459 [ run ] triggered by Bot |
- Updated L0_Test.groovy to include auto_trigger for Qwen3Next. - Added TestQwen3NextThinking class in test_llm_api_pytorch.py for accuracy testing. - Updated l0_dgx_h100.yml to include new test case for Qwen3Next under specific conditions. Signed-off-by: Robin Kobus <[email protected]>
Funatiq
force-pushed
the
dev/qwen3-next-test
branch
from
370322e to
d4acfd0
Compare
|
/bot run --stage-list "DGX_H100-4_GPUs-PyTorch-Qwen3Next-1" |
|
PR_Github #20460 [ run ] triggered by Bot |
|
PR_Github #20459 [ run ] completed with state |
|
PR_Github #20460 [ run ] completed with state |
📝 WalkthroughWalkthroughAdds Qwen3Next test support across CI and integration tests: Jenkins pipeline maps “-Qwen3Next-” stages to auto_trigger=qwen3_next and includes new DGX_H100-4 GPU entries (x86 and Slurm). Introduces a PyTorch accuracy test class for Qwen3-Next-80B-A3B-Thinking and updates GSM8K/MMLU reference YAMLs. Updates DGX H100 L0 test DB to include this test. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant Dev as Developer
participant Jenkins as Jenkins L0 Pipeline
participant Groovy as L0_Test.groovy
participant Mako as Mako Args
participant DB as test-db/l0_dgx_h100.yml
participant Slurm as Slurm Launcher
participant PyTest as pytest
participant Tests as TestQwen3NextThinking
Dev->>Jenkins: Push/PR triggers CI
Jenkins->>Groovy: Stage “...-Qwen3Next-...”
Groovy->>Mako: getMakoArgsFromStageName()
Note right of Groovy: Sets auto_trigger=qwen3_next
Mako-->>Jenkins: Args with qwen3_next
Jenkins->>DB: Resolve matching pre_merge block (4x H100, PyTorch)
DB-->>Jenkins: Qwen3Next test spec
Jenkins->>Slurm: Launch DGX_H100-4_GPUs-PyTorch-Qwen3Next-1
Slurm->>PyTest: Execute selected test
PyTest->>Tests: Run test_auto_dtype (tp/pp/ep, cache, graphs)
Tests-->>PyTest: MMLU/GSM8K results
PyTest-->>Jenkins: Report status
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests
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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
jenkins/L0_Test.groovy (1)
1279-1281: Extract Qwen3Next tag to constant
Define a constant to prevent drift with test-db YAML and simplify future reuse:+@Field +def TAG_QWEN3NEXT = "qwen3_next" ... - } else if (stageName.contains("-Qwen3Next-")) { - makoArgs += ["auto_trigger=qwen3_next"] + } else if (stageName.contains("-Qwen3Next-")) { + makoArgs += ["auto_trigger=${TAG_QWEN3NEXT}"]
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (5)
jenkins/L0_Test.groovy(2 hunks)tests/integration/defs/accuracy/references/gsm8k.yaml(1 hunks)tests/integration/defs/accuracy/references/mmlu.yaml(1 hunks)tests/integration/defs/accuracy/test_llm_api_pytorch.py(1 hunks)tests/integration/test_lists/test-db/l0_dgx_h100.yml(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/accuracy/test_llm_api_pytorch.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/accuracy/test_llm_api_pytorch.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/accuracy/test_llm_api_pytorch.py
🧠 Learnings (1)
📚 Learning: 2025-08-26T09:49:04.956Z
Learnt from: pengbowang-nv
PR: NVIDIA/TensorRT-LLM#7192
File: tests/integration/test_lists/test-db/l0_dgx_b200.yml:56-72
Timestamp: 2025-08-26T09:49:04.956Z
Learning: In TensorRT-LLM test configuration files, the test scheduling system handles wildcard matching with special rules that prevent duplicate test execution even when the same tests appear in multiple yaml files with overlapping GPU wildcards (e.g., "*b200*" and "*gb200*").
Applied to files:
tests/integration/test_lists/test-db/l0_dgx_h100.yml
🧬 Code graph analysis (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (4)
tests/integration/defs/accuracy/accuracy_core.py (5)
LlmapiAccuracyTestHarness(844-855)MMLU(315-329)evaluate(184-245)evaluate(763-773)GSM8K(332-347)tests/integration/defs/conftest.py (2)
llm_models_root(77-91)get_device_count(1958-1960)tensorrt_llm/llmapi/llm_args.py (2)
KvCacheConfig(1058-1192)CudaGraphConfig(109-166)tensorrt_llm/llmapi/llm.py (1)
LLM(1048-1064)
🔇 Additional comments (6)
tests/integration/defs/accuracy/references/gsm8k.yaml (1)
126-127: LGTM: reference added for Qwen3Next (GSM8K).Format, placement, and value style look consistent with surrounding entries.
Please confirm this accuracy was obtained with the same eval settings used for other entries (dataset split, few‑shot, normalization).
tests/integration/defs/accuracy/references/mmlu.yaml (1)
232-233: LGTM: reference added for Qwen3Next (MMLU).Insertion point and formatting align with file conventions.
Please confirm the score uses the standard MMLU config (NUM_SAMPLES, seed, prompt setup) for parity with existing rows.
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
3562-3591: Qwen3Next thinking test: configuration and gating look sound.
- Device-count check prevents misconfigured world sizes.
- Conservative KV reuse setting and cuda graph padding are reasonable for CI.
Minor: 720 as cuda_graph max_batch_size is unusual vs. nearby tests (often <= 512). If intentional (workload fit), ignore; otherwise consider 512 for consistency.
jenkins/L0_Test.groovy (1)
2053-2054: Verify test-list rendering for DGX_H100-4_GPUs-PyTorch-Qwen3Next-1
Grep confirms the stage is defined, but please execute the actual dry-run of your test-list rendering (e.g., invokerenderTestDBor the Jenkins pipeline in dry-run mode) for this stage and confirm the output contains only Qwen3Next tests.tests/integration/test_lists/test-db/l0_dgx_h100.yml (2)
167-167: LGTM on added GPT‑OSS case.Entry is consistent with neighboring GPT‑OSS tests for 4×H100.
168-181: New qwen3_next block is correctly configured
- test existence, parameterization, and CI wiring verified; no duplicates found
- optional: append
TIMEOUT (120)to the test entry for long-running accuracy tests
|
/bot run |
|
PR_Github #20465 [ run ] triggered by Bot |
Signed-off-by: Faradawn Yang <[email protected]>
|
PR_Github #20465 [ run ] completed with state |
Signed-off-by: Faradawn Yang <[email protected]>
Signed-off-by: Faradawn Yang <[email protected]>
Signed-off-by: Faradawn Yang <[email protected]>
Summary by CodeRabbit
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.
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 thestage-listparameter 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.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip 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-pipelineReuse 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.