[https://nvbugs/5390853][fix] Fix _test_openai_lora.py - disable cuda graph #6965
Conversation
Signed-off-by: Amit Zuker <[email protected]>
📝 WalkthroughWalkthroughA test file was updated to include a new top-level option "cuda_graph_config": None in extra_llm_api_options_dict, alongside the existing "lora_config", with comments noting CUDA graph is disabled and a TODO to remove later. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Possibly related PRs
Suggested reviewers
Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. ✨ 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
|
amitz-nv
changed the title
|
/bot run |
|
PR_Github #15530 [ run ] triggered by Bot |
![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/unittest/llmapi/apps/_test_openai_lora.py (3)
33-35: Use a unique temp file to avoid collisions and symlink risks in /tmpUsing a fixed filename in the system temp dir can collide across parallel test runs and is susceptible to TOCTOU/symlink issues. Prefer
mkstemp/NamedTemporaryFile(delete=False)to create a unique, secure path.Here’s a drop-in replacement for the fixture body:
fd, temp_file_path = tempfile.mkstemp(prefix="extra_llm_api_options_", suffix=".yaml") os.close(fd) try: with open(temp_file_path, "w") as f: yaml.safe_dump(extra_llm_api_options_dict, f, sort_keys=False) yield temp_file_path finally: try: os.remove(temp_file_path) except FileNotFoundError: pass
48-49: Prefer yaml.safe_dump and keep key order for readability
yaml.safe_dumpavoids serializing arbitrary Python objects and is generally safer for configs. Preserving key order can aid debugging.Apply this diff:
- with open(temp_file_path, 'w') as f: - yaml.dump(extra_llm_api_options_dict, f) + with open(temp_file_path, 'w') as f: + yaml.safe_dump(extra_llm_api_options_dict, f, sort_keys=False)
1-1: Add NVIDIA copyright headerThe coding guidelines require an NVIDIA copyright header on source files. Add the current year.
Apply this diff at the top of the file:
+# Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
📜 Review details
Configuration used: .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/unittest/llmapi/apps/_test_openai_lora.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+
Python indentation: 4 spaces, no tabs
Maintain module namespace in imports (from package.subpackage import foo; then use foo.SomeClass())
Python file names use snake_case
Python class names use PascalCase
Python functions/methods and local variables use snake_case; variables starting with a number get k_ prefix (e.g., k_99th_percentile)
Global variables use G_ prefixed UPPER_SNAKE_CASE (e.g., G_MY_GLOBAL)
Constants use UPPER_SNAKE_CASE in Python
Avoid shadowing variables from outer scopes in Python
Initialize all externally visible members of a Python class in init
Prefer docstrings for interfaces used outside a file; comments for local code
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes/variables inline with short docstrings
Avoid reflection when simple alternatives exist (e.g., prefer explicit parameters over dict(**locals()))
In try/except, catch the narrowest exceptions possible
For duck-typing with try/except, keep try body minimal and put logic in else
Files:
tests/unittest/llmapi/apps/_test_openai_lora.py
**/*.{cpp,cxx,cc,cu,h,hpp,hxx,hh,cuh,py}
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header (current year) to all source files
Files:
tests/unittest/llmapi/apps/_test_openai_lora.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/unittest/llmapi/apps/_test_openai_lora.py (2)
42-46: LGTM: Explicitly disabling CUDA Graph for this test is reasonableAdding
cuda_graph_config: Nonein the per-test extra options is a minimal, targeted way to disable CUDA Graphs for this LoRA test without affecting other tests.
43-46: No change required —cuda_graph_config: nullis handled safelyShort summary: I inspected the code paths that load, merge, and consume extra LLM API options. YAML null -> Python None is accepted and guarded against; there are no places that unconditionally subscripts a dict out of
cuda_graph_config.Checked locations:
- tensorrt_llm/llmapi/llm_args.py
- validate_cuda_graph_config (around lines ~2245–2261): returns immediately if self.cuda_graph_config is None.
- get_pytorch_backend_config (around lines ~2336–2347): uses conditional expressions (if self.cuda_graph_config else ) to avoid dereferencing None.
- update_llm_args_with_extra_options / update_llm_args_with_extra_dict (around lines ~2397–2436): YAML is merged into the llm_args dict; conversion into typed submodels occurs when LlmArgs.from_kwargs is used.
- tensorrt_llm/commands/serve.py (around lines ~326–331): --extra_llm_api_options YAML is loaded and merged via update_llm_args_with_extra_dict before constructing the LLM.
Repository search:
- No occurrences found of dict-style subscripting (e.g., llm_args['cuda_graph_config'][...]) or .get("cuda_graph_config") that would dereference None before the Pydantic model/validators run.
Conclusion: Passing
cuda_graph_config: null(Python None) disables CUDA graphs as intended and the codebase guards against dereferencing it.
|
PR_Github #15530 [ run ] completed with state |
Description
Disable CUDA graph in
_test_openai_lora.pyas CUDA graph is not supported with LoRA.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.
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.