[TRTQA-2920][chore] improve hang tests #6781
Conversation
📝 WalkthroughWalkthroughReplace static device-skip decorators with runtime device-count checks for two parallelism tests, add eight-device Changes
Sequence Diagram(s)sequenceDiagram
participant Runner as pytest runner
participant Env as Device environment
participant Test as Test function
Runner->>Env: get_device_count()
Env-->>Runner: device_count
Runner->>Test: compute required = (tp*pp*2) or (ctx_pp*gen_tp*2)
alt required > device_count
Runner->>Test: pytest.skip("Not enough devices for ...")
else
Runner->>Test: execute test body
end
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Suggested labels
Suggested reviewers
📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (2)
⏰ 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)
✨ 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
|
xinhe-nv
force-pushed
the
user/xinhe/fix
branch
from
b48f6d7 to
e05f79c
Compare
|
/bot run |
|
PR_Github #14760 [ run ] triggered by Bot |
xinhe-nv
force-pushed
the
user/xinhe/fix
branch
from
e05f79c to
c823cf3
Compare
|
PR_Github #14760 [ run ] completed with state |
![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 (2)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (2)
252-254: Redundant explicit enable_block_reuse=True; default is already TrueKvCacheConfig defaults enable_block_reuse to True. Unless you’re documenting intent, you can drop it for brevity.
- kv_cache_config = KvCacheConfig( - enable_block_reuse=True, free_gpu_memory_fraction=0.8 - ) # both one-model and two-model supports this feature + kv_cache_config = KvCacheConfig( + free_gpu_memory_fraction=0.8 + ) # both one-model and two-model supports this feature
283-285: Add rationale comment for disabling block reuse in n-gram testA short note helps future readers understand why reuse is disabled here and why 80% memory cap was chosen.
- kv_cache_config = KvCacheConfig(enable_block_reuse=False, - free_gpu_memory_fraction=0.8) + # Disable block reuse to isolate n-gram speculative decoding behavior and reduce flakiness; + # cap KV cache to 80% to leave headroom for graphs/buffers. + kv_cache_config = KvCacheConfig(enable_block_reuse=False, + free_gpu_memory_fraction=0.8)
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
tests/integration/defs/accuracy/test_disaggregated_serving.py(3 hunks)tests/integration/defs/accuracy/test_llm_api_pytorch.py(2 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- tests/integration/defs/accuracy/test_disaggregated_serving.py
🧰 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/integration/defs/accuracy/test_llm_api_pytorch.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/integration/defs/accuracy/test_llm_api_pytorch.py
🧬 Code Graph Analysis (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
tensorrt_llm/llmapi/llm_args.py (1)
KvCacheConfig(923-1018)
⏰ 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
xinhe-nv
force-pushed
the
user/xinhe/fix
branch
from
c823cf3 to
3dcd0e4
Compare
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (2)
252-254: Nit: grammar in trailing commentChange “supports” → “support”.
- ) # both one-model and two-model supports this feature + ) # both one-model and two-model support this feature
283-284: Optional: add a brief rationale comment for 0.8Documenting the intent can help future maintainers.
- kv_cache_config = KvCacheConfig(enable_block_reuse=False, - free_gpu_memory_fraction=0.8) + kv_cache_config = KvCacheConfig( + enable_block_reuse=False, + free_gpu_memory_fraction=0.8, # leave ~20% GPU mem headroom to prevent near-OOM/hangs in CI + )
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
tests/integration/defs/accuracy/test_disaggregated_serving.py(3 hunks)tests/integration/defs/accuracy/test_llm_api_pytorch.py(2 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- tests/integration/defs/accuracy/test_disaggregated_serving.py
🧰 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/integration/defs/accuracy/test_llm_api_pytorch.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/integration/defs/accuracy/test_llm_api_pytorch.py
🧬 Code Graph Analysis (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
tensorrt_llm/llmapi/llm_args.py (1)
KvCacheConfig(923-1018)
⏰ 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/accuracy/test_llm_api_pytorch.py (2)
252-254: LGTM: bound KV cache to 80% for EAGLE3Adding free_gpu_memory_fraction=0.8 is valid and aligns with KvCacheConfig behavior. This should help avoid near-OOM/hangs without affecting accuracy.
283-284: LGTM: explicit KV cache headroom for NGram decodeSetting free_gpu_memory_fraction=0.8 with reuse disabled is reasonable to reduce memory pressure during speculative decoding.
xinhe-nv
force-pushed
the
user/xinhe/fix
branch
from
3dcd0e4 to
1ee4476
Compare
|
/bot run |
|
PR_Github #14909 [ run ] triggered by Bot |
xinhe-nv
force-pushed
the
user/xinhe/fix
branch
from
1ee4476 to
3e3aeab
Compare
|
PR_Github #14909 [ run ] completed with state |
xinhe-nv
force-pushed
the
user/xinhe/fix
branch
from
3e3aeab to
67d5efb
Compare
|
/bot run |
|
PR_Github #14936 [ run ] triggered by Bot |
Signed-off-by: Xin He (SW-GPU) <[email protected]>
xinhe-nv
force-pushed
the
user/xinhe/fix
branch
from
67d5efb to
d5b0b45
Compare
|
PR_Github #14936 [ run ] completed with state |
4 participants
Summary by CodeRabbit
New Features
Tests
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.