[https://nvbugs/5383702][fix] error propagation in GenerationExecutor #6793
Conversation
📝 WalkthroughWalkthroughStandardizes executor initialization status messaging to a 2-tuple (status, traceback), updates proxy to consume and act on it, and adds a unit test validating error propagation when worker initialization fails. Changes
Sequence Diagram(s)sequenceDiagram
participant Client as LLM initializer
participant Proxy as GenerationExecutorProxy
participant Worker as GenerationExecutorWorker
participant Q as worker_init_status_queue
Client->>Proxy: start executor workers
Proxy->>Worker: spawn/initialize
alt Worker init fails
Worker-->>Q: (error_obj, traceback_str)
Proxy->>Q: get()
Q-->>Proxy: (status!=READY, error_trace)
Proxy->>Proxy: log error with traceback
Proxy->>MPI: abort(reason=status)
Proxy-->>Client: raise RuntimeError
else Worker init succeeds
Worker-->>Q: (READY, None)
Proxy->>Q: get()
Q-->>Proxy: (READY, None)
Proxy-->>Client: continue initialization
end
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes 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 comments)
Other keywords and placeholders
Documentation and Community
|
Signed-off-by: Superjomn <[email protected]>
Signed-off-by: Superjomn <[email protected]>
Superjomn
force-pushed
the
fix-propagation
branch
from
a27d0f8 to
5683e94
Compare
|
/bot run |
|
PR_Github #14797 [ 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: 2
🔭 Outside diff range comments (1)
tests/unittest/llmapi/test_llm_pytorch.py (1)
820-832: Simplify patch and fix unused variable; ensure no heavy init happensRaise directly from the patched factory and remove the unused variable assignment flagged by Ruff (F841).
- # Test that the error is properly caught and re-raised by LLM - # We patch GenerationExecutor.create directly to return our failing worker - with patch('tensorrt_llm.executor.executor.GenerationExecutor.create', - side_effect=lambda *args, **kwargs: FailingExecutorWorker( - *args, **kwargs)): - with pytest.raises( - RuntimeError, - match="Mock GenerationExecutorWorker initialization failed"): - llm = LLM(model=llama_model_path, - kv_cache_config=global_kvcache_config) + # Patch the executor factory to fail immediately (no engine/GPU work). + with patch('tensorrt_llm.executor.executor.GenerationExecutor.create', + side_effect=RuntimeError("Mock GenerationExecutorWorker initialization failed")): + with pytest.raises(RuntimeError, + match="Mock GenerationExecutorWorker initialization failed"): + LLM(model=llama_model_path, kv_cache_config=global_kvcache_config)
🧹 Nitpick comments (7)
tensorrt_llm/executor/proxy.py (2)
327-332: Harden abort reason typing and exception chaining
- Pass a string to shutdown_abort; don’t rely on implicit str(Exception).
- Only use “raise … from …” if the status is an Exception; otherwise include the status representation in the message. Also enrich logging with the status repr.
- if ready_signal != GenerationExecutorProxy.READY_SIGNAL: - logger.error(f"Executor worker initialization error: {error_trace}") - self.mpi_session.shutdown_abort(reason=ready_signal) - raise RuntimeError( - "Executor worker returned error") from ready_signal + if status != GenerationExecutorProxy.READY_SIGNAL: + logger.error( + f"Executor worker initialization error: status={status!r}, trace:\n{error_trace}" + ) + self.mpi_session.shutdown_abort(reason=str(status)) + if isinstance(status, Exception): + raise RuntimeError("Executor worker returned error") from status + else: + raise RuntimeError(f"Executor worker returned error: {status!r}")
1-1: Missing NVIDIA copyright headerPer project guidelines, add the NVIDIA copyright header at the top.
tensorrt_llm/executor/worker.py (3)
777-783: Consider a more robust wire format for errorsPickling arbitrary Exceptions across process boundaries can fail for some exception types. A robust approach is to serialize the exception class name and message, and keep the full traceback string; reconstruct or wrap upstream.
Example shape: ({"exc_type": type(e).name, "message": str(e)}, traceback.format_exc())
645-650: Fix type annotation for ready_signalProxy uses a bytes READY signal (b"READY"). Update the worker_main signature to reflect bytes.
- ready_signal: Optional[str] = None, + ready_signal: Optional[bytes] = None,
1-1: Missing NVIDIA copyright headerPer project guidelines, add the NVIDIA copyright header at the top.
tests/unittest/llmapi/test_llm_pytorch.py (2)
6-6: Avoid symbol import; keep namespace per guidelines (or remove entirely)The direct symbol import breaks the “maintain namespace” guideline and is unnecessary if you raise directly in the patched factory (see below). Remove this import.
-from tensorrt_llm.executor import GenerationExecutorWorker
814-832: Optional: add a unit test that exercises the proxy’s 2-tuple init handshakeCurrent test fails early in the factory and does not cover the new (status, traceback) path via worker_init_status_queue. Consider adding a focused unit test that constructs a GenerationExecutorProxy with mocked mpi_session and worker_init_status_queue to return (Exception(...), "trace..."), then asserts the raised RuntimeError and logging.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
tensorrt_llm/executor/proxy.py(1 hunks)tensorrt_llm/executor/worker.py(2 hunks)tests/unittest/llmapi/test_llm_pytorch.py(2 hunks)
🧰 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/unittest/llmapi/test_llm_pytorch.pytensorrt_llm/executor/worker.pytensorrt_llm/executor/proxy.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/unittest/llmapi/test_llm_pytorch.pytensorrt_llm/executor/worker.pytensorrt_llm/executor/proxy.py
🧠 Learnings (1)
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Applied to files:
tests/unittest/llmapi/test_llm_pytorch.py
🧬 Code Graph Analysis (3)
tests/unittest/llmapi/test_llm_pytorch.py (2)
tensorrt_llm/executor/worker.py (1)
GenerationExecutorWorker(48-631)tensorrt_llm/llmapi/llm.py (1)
LLM(1111-1127)
tensorrt_llm/executor/worker.py (2)
tensorrt_llm/executor/utils.py (1)
put(119-120)tensorrt_llm/executor/ipc.py (2)
put(116-126)put(270-276)
tensorrt_llm/executor/proxy.py (3)
tensorrt_llm/executor/utils.py (1)
get(122-123)tensorrt_llm/logger.py (1)
error(125-126)tensorrt_llm/executor/executor.py (1)
_handle_background_error(244-273)
🪛 Ruff (0.12.2)
tests/unittest/llmapi/test_llm_pytorch.py
829-829: Local variable llm is assigned to but never used
Remove assignment to unused variable llm
(F841)
🔇 Additional comments (2)
tensorrt_llm/executor/worker.py (2)
777-783: Good: propagate both exception object and tracebackThe 2-tuple shape (exc, trace) is clear and enables richer logging upstream.
800-801: Consistent success payloadEmitting (ready_signal, None) on success aligns with the new protocol.
|
PR_Github #14797 [ run ] completed with state |
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…NVIDIA#6793) Signed-off-by: Superjomn <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
3 participants
Summary by CodeRabbit
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.
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.