[fix] Fixes to parameter usage and low latency configuration. #6343
Conversation
📝 WalkthroughWalkthroughThe changes add support for a new backend called "_autodeploy" in the latency benchmarking script. The logic for backend selection is updated to handle this backend, including specific handling of configuration parameters. Logging is introduced to warn when certain configurations are ignored for "_autodeploy" and "pytorch" backends. In the throughput benchmarking script, parameter extraction is changed from Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes Suggested reviewers
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. 📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (1)
✅ Files skipped from review due to trivial changes (1)
⏰ 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
🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
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 (1)
tensorrt_llm/bench/benchmark/low_latency.py (1)
302-315: Well-structured implementation addressing the PR objectives.The changes successfully implement the removal of problematic performance options for both pytorch and _autodeploy backends, which aligns perfectly with the PR objectives to fix validation errors. The code maintains consistency in error handling and logging patterns.
Consider adding explicit validation or documentation about parameter requirements for the _autodeploy backend to make the parameter mapping more robust and self-documenting.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tensorrt_llm/bench/benchmark/low_latency.py(2 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
**/*.py: The code developed for TensorRT-LLM 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 file, prefer docstrings over comments in Python.
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 docstring for the class.
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:
tensorrt_llm/bench/benchmark/low_latency.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. The block should be prepended to the top of all files, including .cpp, .h, .cu, .py, and any other source files which are compiled or interpreted.
Files:
tensorrt_llm/bench/benchmark/low_latency.py
🧠 Learnings (1)
tensorrt_llm/bench/benchmark/low_latency.py (1)
Learnt from: CR
PR: NVIDIA/TensorRT-LLM#0
File: CODING_GUIDELINES.md:0-0
Timestamp: 2025-07-24T15:02:41.540Z
Learning: Applies to **/*.py : The code developed for TensorRT-LLM should conform to Python 3.8+.
🔇 Additional comments (3)
tensorrt_llm/bench/benchmark/low_latency.py (3)
16-16: LGTM! Import follows proper conventions.The import statement correctly maintains the namespace and follows the existing pattern for LLM class imports in the file.
302-305: LGTM! Proper handling of performance configuration removal.The code correctly removes the problematic
extended_runtime_perf_knob_configfor the pytorch backend with appropriate warning logging. The use ofkwargs.pop()withNonedefault ensures safe removal regardless of whether the key exists.
307-315: Verify AutoDeployLLM Constructor Supports Mapped ParametersI wasn’t able to locate the
AutoDeployLLMdefinition in the repository—please confirm that its constructor:
- accepts a
world_sizeargument (and cleanly handles whentensor_parallel_sizeis absent)- does not require
pipeline_parallel_size- ignores
extended_runtime_perf_knob_configwith a warningThis will ensure the new
_autodeploybackend mapping is correct.
|
/bot run |
|
PR_Github #12970 [ run ] triggered by Bot |
|
PR_Github #12970 [ run ] completed with state |
Signed-off-by: Frank Di Natale <[email protected]>
Signed-off-by: Frank Di Natale <[email protected]>
FrankD412
force-pushed
the
fdinatale/trtllm-bench/remove_perfopts_from_latency
branch
from
521f469 to
0df9333
Compare
FrankD412
changed the title
|
/bot run |
|
PR_Github #13032 [ run ] triggered by Bot |
|
PR_Github #13032 [ run ] completed with state |
|
/bot run |
|
PR_Github #13046 [ run ] triggered by Bot |
|
PR_Github #13046 [ run ] completed with state |
|
/bot run |
|
PR_Github #13263 [ run ] triggered by Bot |
|
PR_Github #13263 [ run ] completed with state |
|
/bot reuse-pipeline |
|
PR_Github #13298 [ reuse-pipeline ] triggered by Bot |
|
PR_Github #13298 [ reuse-pipeline ] completed with state |
FrankD412
deleted the
fdinatale/trtllm-bench/remove_perfopts_from_latency
branch
…#6343) Signed-off-by: Lanyu Liao <[email protected]>
4 participants
Summary by CodeRabbit
New Features
Improvements
Description
This PR adds some changes that remove the extended performance options from the PyTorch and AutoDeploy flows to the low latency benchmark. We cannot pass these options to the backends due to validation errors which currently prevents the benchmark from running.
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.
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.