[https://nvbugs/5560921][fix] GenerationExecutor RPC #8209
Conversation
|
/bot run |
📝 WalkthroughWalkthroughIntroduces two static helper methods on GenerationExecutor to centralize creation of RPC and IPC executors, refactors create logic to use them, and tightens orchestrator_type checking. Re-enables previously skipped RPC-related tests by removing skip markers in two test modules. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor Client
participant GenExec as GenerationExecutor.create
participant Config as Config/Args
participant RPC as GenerationExecutorRpcProxy
participant IPCProxy as GenerationExecutorProxy
participant IPCWorker as GenerationExecutorWorker
Client->>GenExec: create(config)
GenExec->>Config: Inspect orchestrator_type, worker mode
alt orchestrator_type == "rpc"
note over GenExec,RPC: New helper path
GenExec->>RPC: _create_rpc_executor(worker_kwargs, ...)
RPC-->>GenExec: RPC proxy instance
else IPC path
alt use_worker == true
note over GenExec,IPCWorker: Single-process worker mode
GenExec->>IPCWorker: _create_ipc_executor(..., use_worker=true)
IPCWorker-->>GenExec: Worker instance
else use_worker == false
note over GenExec,IPCProxy: IPC proxy mode
GenExec->>IPCProxy: _create_ipc_executor(..., use_worker=false)
IPCProxy-->>GenExec: Proxy instance
end
end
GenExec-->>Client: Executor handle
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 (beta)
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: 1
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
tensorrt_llm/executor/executor.py(5 hunks)tests/unittest/llmapi/test_llm_multi_gpu_pytorch.py(0 hunks)tests/unittest/llmapi/test_llm_pytorch.py(0 hunks)
💤 Files with no reviewable changes (2)
- tests/unittest/llmapi/test_llm_multi_gpu_pytorch.py
- tests/unittest/llmapi/test_llm_pytorch.py
🧰 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:
tensorrt_llm/executor/executor.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:
tensorrt_llm/executor/executor.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:
tensorrt_llm/executor/executor.py
🧬 Code graph analysis (1)
tensorrt_llm/executor/executor.py (7)
tensorrt_llm/llmapi/mpi_session.py (1)
MpiSession(84-129)tensorrt_llm/executor/postproc_worker.py (1)
PostprocWorkerConfig(42-49)tensorrt_llm/llmapi/llm_args.py (1)
KvCacheConnectorConfig(421-433)tensorrt_llm/executor/rpc_proxy.py (1)
GenerationExecutorRpcProxy(24-375)tensorrt_llm/executor/worker.py (1)
GenerationExecutorWorker(41-229)tensorrt_llm/executor/proxy.py (1)
GenerationExecutorProxy(37-449)tensorrt_llm/executor/utils.py (1)
ProcessPoolExecutorSession(80-104)
⏰ 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 (6)
tensorrt_llm/executor/executor.py (6)
378-395: LGTM!The helper method cleanly centralizes RPC executor creation with appropriate parameters and a clear docstring.
396-426: LGTM!The helper method appropriately abstracts IPC executor creation with clear documentation on the
use_workerparameter controlling single-process vs. multi-process modes.
500-515: LGTM!The refactored calls to
_create_rpc_executorand_create_ipc_executorcorrectly handle the spawn_workers/mpirun_launch path with appropriate parameters.
526-541: LGTM!The return_logits/single-process TP1 path correctly uses
use_worker=Truefor_create_ipc_executorto create a single-process worker, appropriately handling the performance optimization mentioned in the comment at line 517-520.
549-564: LGTM!The non-Windows default path correctly uses the helper methods with
mpi_session=None(line 560) to leverage mpi4py for IPC communication.
570-578: Note: RPC support for Windows is pending.The TODO comment at line 570 indicates that RPC executor support for Windows is not yet implemented. Currently, only IPC executor is created for Windows platforms.
Is RPC support for Windows planned, or should this TODO be tracked in a separate issue?
tensorrt_llm/executor/executor.py
Outdated
| elif orchestrator_type != "rpc": | ||
| raise ValueError( | ||
| f"Unsupported orchestrator_type: {orchestrator_type}") |
There was a problem hiding this comment.
Logic error: rejecting valid orchestrator_type=None.
The change from checking orchestrator_type is None to orchestrator_type != "rpc" introduces a breaking change. When llm_args is not a TorchLlmArgs instance (line 475-476), orchestrator_type is None, which was previously a valid value indicating the default IPC executor should be used. Now it raises ValueError("Unsupported orchestrator_type: None").
Apply this diff to allow None while still rejecting invalid orchestrator types:
- elif orchestrator_type != "rpc":
+ elif orchestrator_type is not None and orchestrator_type != "rpc":
raise ValueError(
f"Unsupported orchestrator_type: {orchestrator_type}")📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| elif orchestrator_type != "rpc": | |
| raise ValueError( | |
| f"Unsupported orchestrator_type: {orchestrator_type}") | |
| elif orchestrator_type is not None and orchestrator_type != "rpc": | |
| raise ValueError( | |
| f"Unsupported orchestrator_type: {orchestrator_type}") |
🧰 Tools
🪛 Ruff (0.13.3)
486-487: Avoid specifying long messages outside the exception class
(TRY003)
🤖 Prompt for AI Agents
In tensorrt_llm/executor/executor.py around lines 485 to 487, the current check
rejects orchestrator_type being None (which should be allowed to select the
default IPC executor); change the conditional so None is permitted but any value
other than "rpc" is rejected. Concretely, replace the current equality check
with a guarded condition that only raises a ValueError when orchestrator_type is
not None and orchestrator_type != "rpc", keeping the original error message for
invalid values.
|
PR_Github #20846 [ run ] triggered by Bot |
|
PR_Github #20846 [ run ] completed with state |
|
/bot run |
|
PR_Github #20866 [ run ] triggered by Bot |
|
PR_Github #20866 [ run ] completed with state |
Signed-off-by: Superjomn <[email protected]>
|
/bot run |
|
PR_Github #20900 [ run ] triggered by Bot |
|
PR_Github #20900 [ run ] completed with state |
Summary by CodeRabbit
Refactor
Tests
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.