[#7692][fix] recognize RequestError as per-request error in background handler #7726
Conversation
|
/bot run |
|
PR_Github #18614 [ run ] triggered by Bot |
📝 WalkthroughWalkthroughRefactors background error handling to distinguish per-request errors from serious ones, adjusts response type checks, and conditionally wraps worker responses only on success. Tests are updated to expose additional public symbols and to cover per-request and submission-time error scenarios, with renamed tests and new dummy classes. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor Client
participant Worker as GenerationExecutorWorker
participant Exec as Executor
participant BG as Background Task/Thread
rect rgba(230,245,255,0.5)
Client->>Worker: Submit request
Worker->>Exec: Enqueue/Process
BG-->>Exec: Error occurs
end
alt Per-request error (RequestError or str)
note over BG,Exec: Per-request error path (no shutdown)
Exec->>Exec: If str, wrap into RequestError
Exec-->>Worker: Propagate per-request error
Worker-->>Client: Error response (unwrapped)
else Serious background error (non-RequestError / non-BaseException)
note over BG,Exec: Serious error path
Exec->>Exec: If non-BaseException, wrap in RuntimeError(repr(error))
Exec->>Exec: Shutdown LLM
Exec-->>Worker: Raise error
Worker-->>Client: Failure (service shutting down)
end
sequenceDiagram
autonumber
actor Client
participant Worker as GenerationExecutorWorker
Client->>Worker: Handle response
alt Response has no error
Worker->>Worker: _maybe_wrap_response(response)
Worker-->>Client: Wrapped success (e.g., logprobs/metrics)
else Response is error
Worker-->>Client: Pass-through error (no wrapping)
end
Estimated code review effort🎯 4 (Complex) | ⏱️ ~60 minutes ✨ Finishing touches
🧪 Generate unit tests
Tip 👮 Agentic pre-merge checks are now available in preview!Pro plan users can now enable pre-merge checks in their settings to enforce checklists before merging PRs.
Please see the documentation for more information. Example: reviews:
pre_merge_checks:
custom_checks:
- name: "Undocumented Breaking Changes"
mode: "warning"
instructions: |
Pass/fail criteria: All breaking changes to public APIs, CLI flags, environment variables, configuration keys, database schemas, or HTTP/GraphQL endpoints must be documented in the "Breaking Change" section of the PR description and in CHANGELOG.md. Exclude purely internal or private changes (e.g., code not exported from package entry points or explicitly marked as internal).Please share your feedback with us on this Discord post. 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 Pre-merge checks❌ Failed checks (2 warnings, 1 inconclusive)
✅ Passed checks (2 passed)
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
🧹 Nitpick comments (2)
tensorrt_llm/executor/worker.py (1)
889-894: Ensure ErrorResponse is serializable and type-consistent.The NamedTuple defines error_msg: str, but an Exception object is put into the queue. Use str(e) to avoid pickling surprises and match the type.
Apply this diff:
- worker._await_response_helper.temp_error_responses.put( - ErrorResponse(req.id, e, req.id)) + worker._await_response_helper.temp_error_responses.put( + ErrorResponse(req.id, str(e), req.id))tensorrt_llm/executor/executor.py (1)
255-276: Per-request vs background error handling looks correct; minor f-string nit for ruff RUF010.Use explicit conversion flags in f-strings instead of repr() to satisfy linters.
Apply this diff:
- print_colored(f"Got per-request error: {repr(error)}\n", + print_colored(f"Got per-request error: {error!r}\n", "red") @@ - print_colored(f"Got per-request error: {repr(error)}\n", + print_colored(f"Got per-request error: {error!r}\n", "red") @@ - print_colored( - f"Got background error: {repr(error)}, will shutdown the LLM instance\n", + print_colored( + f"Got background error: {error!r}, will shutdown the LLM instance\n", "red")
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
tensorrt_llm/executor/executor.py(1 hunks)tensorrt_llm/executor/utils.py(1 hunks)tensorrt_llm/executor/worker.py(1 hunks)tests/unittest/llmapi/test_llm.py(4 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:
tensorrt_llm/executor/utils.pytensorrt_llm/executor/worker.pytensorrt_llm/executor/executor.pytests/unittest/llmapi/test_llm.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/utils.pytensorrt_llm/executor/worker.pytensorrt_llm/executor/executor.pytests/unittest/llmapi/test_llm.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/utils.pytensorrt_llm/executor/worker.pytensorrt_llm/executor/executor.pytests/unittest/llmapi/test_llm.py
🧬 Code graph analysis (3)
tensorrt_llm/executor/worker.py (1)
tensorrt_llm/_torch/pyexecutor/llm_request.py (1)
has_error(280-281)
tensorrt_llm/executor/executor.py (2)
tensorrt_llm/executor/utils.py (1)
RequestError(76-77)tensorrt_llm/llmapi/utils.py (2)
enable_llm_debug(285-290)print_colored(45-61)
tests/unittest/llmapi/test_llm.py (7)
tensorrt_llm/executor/worker.py (3)
abort_request(274-283)_pop_result(641-643)submit(607-639)tensorrt_llm/executor/request.py (2)
GenerationRequest(84-131)LoRARequest(24-53)tensorrt_llm/executor/result.py (3)
GenerationResult(488-637)result(566-577)request_id(524-525)tensorrt_llm/_torch/auto_deploy/shim/demollm.py (2)
abort_request(350-351)submit(335-348)tensorrt_llm/executor/proxy.py (2)
abort_request(148-157)submit(405-430)tensorrt_llm/executor/utils.py (2)
submit(89-94)RequestError(76-77)tensorrt_llm/llmapi/llm.py (2)
LLM(1017-1033)generate(237-315)
🪛 Ruff (0.12.2)
tensorrt_llm/executor/executor.py
258-258: Use explicit conversion flag
Replace with conversion flag
(RUF010)
263-263: Use explicit conversion flag
Replace with conversion flag
(RUF010)
273-273: Use explicit conversion flag
Replace with conversion flag
(RUF010)
tests/unittest/llmapi/test_llm.py
2000-2000: Avoid specifying long messages outside the exception class
(TRY003)
⏰ 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/test_llm.py (2)
1911-1924: Good: error injection now tracks by client_id and uses real request_id.This makes abort routing deterministic and avoids dummy IDs.
1928-1935: Good: preserve queues for failed requests until abort propagates.Prevents losing late backend outputs while cancellation travels.
tongyuantongyu
force-pushed
the
ytong/error-handle-request
branch
from
c392629 to
6b619a3
Compare
|
/bot run |
|
PR_Github #18619 [ run ] triggered by Bot |
|
PR_Github #18614 [ run ] completed with state |
|
PR_Github #18619 [ run ] completed with state |
tongyuantongyu
force-pushed
the
ytong/error-handle-request
branch
from
6b619a3 to
223e9ea
Compare
|
/bot run |
2 similar comments
|
/bot run |
|
/bot run |
|
PR_Github #18768 [ run ] triggered by Bot |
|
PR_Github #18768 [ run ] completed with state |
tongyuantongyu
force-pushed
the
ytong/error-handle-request
branch
from
223e9ea to
b37bf73
Compare
|
/bot run |
|
PR_Github #18868 [ run ] triggered by Bot |
tongyuantongyu
force-pushed
the
ytong/error-handle-request
branch
from
b37bf73 to
3790dbf
Compare
|
/bot run |
|
PR_Github #18877 [ run ] triggered by Bot |
|
PR_Github #18868 [ run ] completed with state |
|
PR_Github #18877 [ run ] completed with state |
…kground handler Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com>
tongyuantongyu
force-pushed
the
ytong/error-handle-request
branch
from
3790dbf to
7d34e70
Compare
|
/bot run |
|
PR_Github #18987 [ run ] triggered by Bot |
|
PR_Github #18987 [ run ] completed with state |
|
/bot run |
1 similar comment
|
/bot run |
|
PR_Github #19095 [ run ] triggered by Bot |
|
PR_Github #19096 [ run ] triggered by Bot |
|
PR_Github #19095 [ run ] completed with state |
|
PR_Github #19096 [ run ] completed with state |
|
/bot run |
|
PR_Github #19324 [ run ] triggered by Bot |
|
PR_Github #19324 [ run ] completed with state |
…quest Signed-off-by: Yuan Tong <13075180+tongyuantongyu@users.noreply.github.com> # Conflicts: # tensorrt_llm/executor/worker.py
|
/bot run |
|
PR_Github #19433 [ run ] triggered by Bot |
|
PR_Github #19433 [ run ] completed with state |
|
/bot run |
|
PR_Github #19472 [ run ] triggered by Bot |
|
PR_Github #19472 [ run ] completed with state |
|
/bot run |
|
PR_Github #19647 [ run ] triggered by Bot |
|
PR_Github #19647 [ run ] completed with state |
3 participants
Summary by CodeRabbit
Description
Fix #7692. Also fix https://nvbugs/5063025.
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.
Details
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.