[None][test] Add accuracy evaluation for AutoDeploy #6764
Conversation
📝 WalkthroughWalkthroughAdds a cached Changes
Sequence Diagram(s)sequenceDiagram
participant TestRunner
participant AutoDeployLLM
participant LlmArgs
participant QuantConfig
participant BenchmarkTask
TestRunner->>AutoDeployLLM: Instantiate (with LlmArgs)
AutoDeployLLM->>LlmArgs: Access .quant_config
alt _quant_config is None
LlmArgs->>QuantConfig: Create QuantConfig instance
LlmArgs-->>LlmArgs: Cache in _quant_config
end
TestRunner->>BenchmarkTask: Run evaluation (CnnDailymail / MMLU)
BenchmarkTask->>AutoDeployLLM: Request generation / streaming
AutoDeployLLM-->>BenchmarkTask: Return responses
BenchmarkTask-->>TestRunner: Report results
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes 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. 📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (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
|
![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 (5)
tensorrt_llm/_torch/auto_deploy/llm_args.py (3)
272-275: Allow resetting quant_config by accepting None in setter (optional)Minor ergonomics: permit assigning None to reset to a default QuantConfig.
@quant_config.setter - def quant_config(self, value: QuantConfig): - self._quant_config = value + def quant_config(self, value: Optional[QuantConfig]): + self._quant_config = QuantConfig() if value is None else value
9-10: Import style nit: keep module namespace per guidelinesPer guidelines, prefer importing the module and referencing names via its namespace.
-from tensorrt_llm.models.modeling_utils import QuantConfig +import tensorrt_llm.models.modeling_utils as modeling_utilsFollow-up edits needed where QuantConfig is referenced (see next comment).
266-271: Follow-up to import style: qualify QuantConfig via module aliasIf adopting the namespaced import, update type hints/usages here.
- def quant_config(self) -> QuantConfig: + def quant_config(self) -> modeling_utils.QuantConfig: - if self._quant_config is None: - self._quant_config = QuantConfig() + if self._quant_config is None: + self._quant_config = modeling_utils.QuantConfig() return self._quant_configAnd adjust the setter signature accordingly if you adopt the previous optional refactor.
tests/integration/defs/accuracy/test_llm_api_autodeploy.py (2)
30-37: Remove commented-out code in test_auto_dtypeAvoid leaving commented blocks in tests; it adds noise.
with AutoDeployLLM(self.MODEL_PATH) as llm: - # task = CnnDailymail(self.MODEL_NAME) - # task.evaluate(llm) task = MMLU(self.MODEL_NAME) task.evaluate(llm)
49-61: Streaming coverage across intervals is valuable; consider adding AutoDeploy streaming (optional)Good to test both detokenization paths. If/when AutoDeploy supports streaming parity here, consider adding an AutoDeployLLM streaming case to mirror this test.
Happy to draft a matching AutoDeploy streaming test if support exists.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
tensorrt_llm/_torch/auto_deploy/llm_args.py(2 hunks)tensorrt_llm/bench/benchmark/throughput.py(0 hunks)tests/integration/defs/accuracy/accuracy_core.py(2 hunks)tests/integration/defs/accuracy/test_llm_api_autodeploy.py(1 hunks)
💤 Files with no reviewable changes (1)
- tensorrt_llm/bench/benchmark/throughput.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/accuracy_core.pytests/integration/defs/accuracy/test_llm_api_autodeploy.pytensorrt_llm/_torch/auto_deploy/llm_args.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/accuracy_core.pytests/integration/defs/accuracy/test_llm_api_autodeploy.pytensorrt_llm/_torch/auto_deploy/llm_args.py
🧠 Learnings (4)
📓 Common learnings
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.
Learnt from: galagam
PR: NVIDIA/TensorRT-LLM#6487
File: tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py:1-12
Timestamp: 2025-08-06T13:58:07.506Z
Learning: In TensorRT-LLM, test files (files under tests/ directories) do not require NVIDIA copyright headers, unlike production source code files. Test files typically start directly with imports, docstrings, or code.
📚 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/integration/defs/accuracy/accuracy_core.pytests/integration/defs/accuracy/test_llm_api_autodeploy.pytensorrt_llm/_torch/auto_deploy/llm_args.py
📚 Learning: 2025-08-06T13:58:07.506Z
Learnt from: galagam
PR: NVIDIA/TensorRT-LLM#6487
File: tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py:1-12
Timestamp: 2025-08-06T13:58:07.506Z
Learning: In TensorRT-LLM, test files (files under tests/ directories) do not require NVIDIA copyright headers, unlike production source code files. Test files typically start directly with imports, docstrings, or code.
Applied to files:
tests/integration/defs/accuracy/accuracy_core.pytests/integration/defs/accuracy/test_llm_api_autodeploy.pytensorrt_llm/_torch/auto_deploy/llm_args.py
📚 Learning: 2025-08-01T15:14:45.673Z
Learnt from: yibinl-nvidia
PR: NVIDIA/TensorRT-LLM#6506
File: examples/models/core/mixtral/requirements.txt:3-3
Timestamp: 2025-08-01T15:14:45.673Z
Learning: In TensorRT-LLM, examples directory can have different dependency versions than the root requirements.txt file. Version conflicts between root and examples dependencies are acceptable because examples are designed to be standalone and self-contained.
Applied to files:
tests/integration/defs/accuracy/accuracy_core.pytests/integration/defs/accuracy/test_llm_api_autodeploy.pytensorrt_llm/_torch/auto_deploy/llm_args.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 (5)
tensorrt_llm/_torch/auto_deploy/llm_args.py (1)
264-271: Good addition: lazy-initialized quant_config for compatibilityProviding a cached QuantConfig via a property keeps llm.args.quant_config always available and non-None, matching existing callers in accuracy code.
tests/integration/defs/accuracy/accuracy_core.py (2)
28-29: Importing AutoDeployLLM for typing support looks goodBrings AutoDeploy into the accuracy framework without touching control flow.
148-152: Broadened evaluate() annotation to include AutoDeployLLMMakes the evaluator accept AutoDeploy-backed LLMs. No functional changes; maintains compatibility with existing callers.
tests/integration/defs/accuracy/test_llm_api_autodeploy.py (2)
26-29: Test harness setup for Llama-3.1-8B looks correctPaths and model naming align with existing test conventions.
38-47: NVFP4 accuracy test assertions are appropriateAsserting llm.args.quant_config.quant_algo ensures the quantized artifact is loaded as intended before evaluation.
svc-trtllm-gh-bot
added
the
Community want to contribute
ajrasane
force-pushed
the
user/arasane/autodeploy_accuracy_eval
branch
2 times, most recently
from
5c534fa to
58302a4
Compare
|
/bot run |
ajrasane
force-pushed
the
user/arasane/autodeploy_accuracy_eval
branch
from
cd1c295 to
d844441
Compare
|
/bot run |
|
PR_Github #15351 [ run ] triggered by Bot |
Signed-off-by: ajrasane <[email protected]>
Signed-off-by: ajrasane <[email protected]>
Signed-off-by: Suyog Gupta <[email protected]>
Signed-off-by: ajrasane <[email protected]>
Signed-off-by: ajrasane <[email protected]>
Signed-off-by: ajrasane <[email protected]>
ajrasane
force-pushed
the
user/arasane/autodeploy_accuracy_eval
branch
from
cf2fec2 to
a226efb
Compare
|
PR_Github #15351 [ run ] completed with state |
|
/bot reuse-pipeline |
|
PR_Github #15466 [ reuse-pipeline ] triggered by Bot |
|
PR_Github #15466 [ reuse-pipeline ] completed with state |
Signed-off-by: ajrasane <[email protected]> Signed-off-by: Suyog Gupta <[email protected]> Co-authored-by: Suyog Gupta <[email protected]>
Signed-off-by: ajrasane <[email protected]> Signed-off-by: Suyog Gupta <[email protected]> Co-authored-by: Suyog Gupta <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: ajrasane <[email protected]> Signed-off-by: Suyog Gupta <[email protected]> Co-authored-by: Suyog Gupta <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: ajrasane <[email protected]> Signed-off-by: Suyog Gupta <[email protected]> Co-authored-by: Suyog Gupta <[email protected]>
Signed-off-by: ajrasane <[email protected]> Signed-off-by: Suyog Gupta <[email protected]> Co-authored-by: Suyog Gupta <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: ajrasane <[email protected]> Signed-off-by: Suyog Gupta <[email protected]> Co-authored-by: Suyog Gupta <[email protected]>
Signed-off-by: ajrasane <[email protected]> Signed-off-by: Suyog Gupta <[email protected]> Co-authored-by: Suyog Gupta <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Summary by CodeRabbit
New Features
Tests
Style
Description
Added accuracy validation test for AutoDeploy
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.