[https://nvbugs/5480415][fix] Fix phi4mm multi-gpu test #7436
Conversation
📝 WalkthroughWalkthroughBroadened the test output parser to accept Generated text in single or double quotes and adjusted capture handling; updated expected image keyword sequences for gemma-3-27b-it and Phi-4-multimodal-instruct in multimodal quickstart tests. All edits are in tests/integration/defs/test_e2e.py. Changes
Sequence Diagram(s)sequenceDiagram
participant T as Test Case
participant P as parse_output
participant R as Regex Matcher
participant S as Test Assertion
T->>P: supply raw test output
P->>R: run regex (accepts '...' or "..." with MULTILINE)
R-->>P: return matches (outer boundary, inner text)
P-->>T: provide extracted generated text (from group(2))
T->>S: compare extracted text to expected keyword lists
S-->>T: pass/fail
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
✨ 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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
![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 (3)
tests/integration/defs/test_e2e.py (3)
1699-1707: Regex fix looks good; advance by full match to avoid edge casesAccepting both quote styles is correct. To make iteration robust (and avoid re-scanning inside the same block when inner quotes appear), advance using the end of the whole match instead of the end of group(1).
- _, end = match.span(1) + end = match.end(0)Optional: replace the while/search/slice loop with finditer to avoid repeated slicing and improve clarity/perf.
- while True: - match = re.search(r'Generated text: ([\'"])(.*?)\1', item, - re.MULTILINE) - if match is None: - break - _, end = match.span(1) - results.append(match.group(2)) - item = item[end:] + for m in re.finditer(r'Generated text:\s*([\'"])(.*?)\1', item, re.MULTILINE): + results.append(m.group(2))
2340-2344: Updated Gemma-3 expected keywords align with observed outputsThe revised keyword sets for gemma-3-27b-it look consistent and keep 5 tokens per prompt, matching the 4/5 threshold logic.
To reduce future flakiness, consider normalizing punctuation and using a small synonym set (e.g., "wave(s)", "granite/rock") or stemming before matching.
2579-2582: Phi-4-MM 2-GPU keywords now match single-GPU expectationsThis resolves the mismatch with test_ptp_quickstart_multimodal and should stabilize multi-GPU runs.
Factor these shared keyword lists into a single constant to prevent drift between the single-GPU and 2-GPU tests.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
tests/integration/defs/test_e2e.py(3 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.{cpp,cc,cxx,cu,h,hpp,hh,hxx,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.{cpp,cc,cxx,cu,h,hpp,hh,hxx,cuh,py}: Use spaces only; no tabs; indent with 4 spaces
Prepend NVIDIA copyright header (current year) to all source files (.cpp, .h, .cu, .py, etc.)
Files:
tests/integration/defs/test_e2e.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+
Indent Python with 4 spaces; no tabs
Preserve module namespaces when importing: from package.subpackage import foo; then call foo.SomeClass() instead of importing the class directly
Python naming: files snake_case; classes PascalCase; functions/methods snake_case; locals snake_case (prefix k_ when starting with a number); globals UPPER_SNAKE_CASE with G_ prefix; constants UPPER_SNAKE_CASE
Avoid shadowing outer-scope variables; initialize all externally visible members in init
Prefer docstrings for interfaces used outside a file; limit comments to function-internal or file-local interfaces
Use Google-style docstrings for classes and functions; document attributes/variables inline so Sphinx can render them
Avoid reflection when simpler alternatives exist; prefer explicit parameters and return dicts over locals()/dynamic tricks
In try/except, catch the narrowest exceptions possible; keep try bodies minimal and use else for the main logic when doing duck-typing checks
Files:
tests/integration/defs/test_e2e.py
⏰ 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
|
/bot run |
|
/bot kill |
|
PR_Github #17191 [ run ] triggered by Bot |
|
PR_Github #17192 [ kill ] triggered by Bot |
|
PR_Github #17191 [ run ] completed with state |
|
PR_Github #17192 [ kill ] completed with state |
* Fix bug in parse_output. * Fix mismatched keywords in phi4mm multi-gpu test. * Fix mismatched keyworkds in gemma-3-27b-it test. Signed-off-by: Wanli Jiang <[email protected]>
Wanli-Jiang
force-pushed
the
user/williamj/fix-phi4mm-multigpu
branch
from
b3c42ff to
334cd09
Compare
|
/bot run --disable-fail-fast |
There was a problem hiding this comment.
Actionable comments posted: 0
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
tests/integration/defs/test_e2e.py (1)
2563-2568: Gemma-3 (2-GPU) expected keywords not updated to match single-GPU test.This will likely fail when
model_name == "gemma-3-27b-it"since single-GPU expectations were changed above. Update the two lists to stay consistent with the new targets."gemma-3-27b-it": { "image": [ - ["half", "dome", "yosemite", "landmark", "rounded"], - ["flowing", "traffic", "vehicles", "road", "Changi"], + ["image", "famous", "rock", "granite", "landmark"], + ["traffic", "moderate", "heavy", "flowing", "cars"], ], },
🧹 Nitpick comments (1)
tests/integration/defs/test_e2e.py (1)
1694-1707: Regex fix looks correct; consider simplifying loop and avoiding rescans.Current solution works, but the slice-at-opening-quote approach causes unnecessary rescans. Use
finditerwith a compiled pattern to collect all matches in one pass.def parse_output(text): results = [] text_lists = re.split(r"\[\d+\] Prompt:", text) for item in text_lists: item = item.replace(os.linesep, "") - while True: - match = re.search(r'Generated text: ([\'"])(.*?)\1', item, - re.MULTILINE) - if match is None: - break - _, end = match.span(1) - results.append(match.group(2)) - item = item[end:] + pattern = re.compile(r'Generated text:\s*([\'"])(.*?)\1', re.MULTILINE) + for m in pattern.finditer(item): + results.append(m.group(2)) return results
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
tests/integration/defs/test_e2e.py(3 hunks)
🧰 Additional context used
📓 Path-based instructions (4)
**/*
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Filenames compiled into a target must be case-insensitively unique
Files:
tests/integration/defs/test_e2e.py
**/*.{h,hpp,hh,hxx,cc,cpp,cxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Use spaces, not tabs; indent 4 spaces
Files:
tests/integration/defs/test_e2e.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Code must target Python 3.8+
Indent with 4 spaces; do not use tabs (Python)
Maintain module namespace on import: prefer from package.subpackage import foo; use foo.Symbol()
Python filenames use snake_case
Python class names use PascalCase
Python functions and methods use snake_case
Python local variables use snake_case; if starting with a number concept, prefix with k (e.g., k_99th_percentile)
Python global variables use G_ prefix with UPPER_SNAKE_CASE
Python constants use UPPER_SNAKE_CASE
Avoid shadowing variables from outer scopes
Initialize all externally visible class members in init
For public interfaces, prefer docstrings over comments; comments should be for in-function or file-local interfaces
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes and variables inline with docstrings immediately after assignment
Avoid reflection when a non-reflective approach suffices
Limit except clauses to specific exceptions where possible
When using try/except for duck-typing, keep try body minimal and move logic to else
Files:
tests/integration/defs/test_e2e.py
**/*.{cpp,cc,cxx,h,hpp,hh,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header (current year) to all source files
Files:
tests/integration/defs/test_e2e.py
⏰ 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 (2)
tests/integration/defs/test_e2e.py (2)
2339-2345: Updated Gemma-3 expected keywords (image) — looks good.Aligns with observed outputs and the PR objective.
2579-2583: Phi-4-MM (2-GPU) expected keywords — aligned with the single-GPU test.Matches the earlier update; should resolve mismatches.
|
PR_Github #17257 [ run ] triggered by Bot |
|
PR_Github #17257 [ run ] completed with state |
3 participants
PR to merge into release/1.0 branch: #7275
PR to merge into main branch: #7256
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.