[TRTLLM-8483][chore] Refine scheduler_config and peft_cache_config in create_py_executor #8451
Conversation
leslie-fang25
force-pushed
the
leslie/refine_scheduler_config_and_peft_cache_config
branch
from
04c632c to
2d772eb
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #21671 [ run ] triggered by Bot |
|
PR_Github #21671 [ run ] completed with state |
📝 WalkthroughWalkthroughThe changes reorganize public API imports, moving Changes
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
🧹 Nitpick comments (3)
tensorrt_llm/_torch/pyexecutor/py_executor_creator.py (2)
218-218: Guard against missing scheduler_config.llm_args.scheduler_config can be None; this is later dereferenced (and also required downstream in create_py_executor_instance). Default it to a fresh SchedulerConfig to avoid NPEs.
Apply:
-from tensorrt_llm.llmapi.llm_args import (CapacitySchedulerPolicy, - KvCacheConnectorConfig, LoadFormat, - PybindMirror, TorchLlmArgs) +from tensorrt_llm.llmapi.llm_args import (CapacitySchedulerPolicy, + KvCacheConnectorConfig, LoadFormat, + PybindMirror, TorchLlmArgs, + SchedulerConfig) - scheduler_config = llm_args.scheduler_config + scheduler_config = llm_args.scheduler_config or SchedulerConfig()
457-461: Chunking policy conversion is correct.Converts to pybind enum when provided; otherwise defaults to FIRST_COME_FIRST_SERVED as intended. Optionally, use getattr(...) to be extra defensive, but not required if you adopt the SchedulerConfig() default above.
tensorrt_llm/_torch/pyexecutor/_util.py (1)
747-747: Pass the effective PEFT config to PyExecutor.You compute peft_cache_config_model (possibly adjusted by LoRA-derived sizes) but pass the original peft_cache_config to PyExecutor. Passing peft_cache_config_model keeps PyExecutor.peft_cache_config aligned with the manager actually created and makes downstream introspection consistent.
Apply:
- peft_cache_config=peft_cache_config) + peft_cache_config=peft_cache_config_model)
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
tensorrt_llm/_torch/pyexecutor/_util.py(5 hunks)tensorrt_llm/_torch/pyexecutor/py_executor.py(1 hunks)tensorrt_llm/_torch/pyexecutor/py_executor_creator.py(3 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/_torch/pyexecutor/py_executor.pytensorrt_llm/_torch/pyexecutor/py_executor_creator.pytensorrt_llm/_torch/pyexecutor/_util.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/_torch/pyexecutor/py_executor.pytensorrt_llm/_torch/pyexecutor/py_executor_creator.pytensorrt_llm/_torch/pyexecutor/_util.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/_torch/pyexecutor/py_executor.pytensorrt_llm/_torch/pyexecutor/py_executor_creator.pytensorrt_llm/_torch/pyexecutor/_util.py
🧠 Learnings (1)
📚 Learning: 2025-08-26T09:37:10.463Z
Learnt from: jiaganc
PR: NVIDIA/TensorRT-LLM#7031
File: tensorrt_llm/bench/dataclasses/configuration.py:90-104
Timestamp: 2025-08-26T09:37:10.463Z
Learning: In TensorRT-LLM, the `get_pytorch_perf_config()` method returns `self.pytorch_config` which can contain default `cuda_graph_config` values, so `llm_args` may already have this config before the extra options processing.
Applied to files:
tensorrt_llm/_torch/pyexecutor/py_executor_creator.py
🧬 Code graph analysis (3)
tensorrt_llm/_torch/pyexecutor/py_executor.py (2)
cpp/include/tensorrt_llm/executor/serialization.h (1)
tensorrt_llm(27-367)tensorrt_llm/llmapi/llm_args.py (1)
PeftCacheConfig(1062-1128)
tensorrt_llm/_torch/pyexecutor/py_executor_creator.py (1)
tensorrt_llm/llmapi/llm_args.py (13)
ContextChunkingPolicy(1004-1010)CapacitySchedulerPolicy(994-1000)_to_pybind(833-834)_to_pybind(989-990)_to_pybind(999-1000)_to_pybind(1009-1010)_to_pybind(1031-1036)_to_pybind(1051-1058)_to_pybind(1115-1128)_to_pybind(1170-1173)_to_pybind(1285-1302)_to_pybind(1358-1364)_to_pybind(1382-1385)
tensorrt_llm/_torch/pyexecutor/_util.py (1)
tensorrt_llm/llmapi/llm_args.py (13)
SchedulerConfig(1040-1058)PeftCacheConfig(1062-1128)_to_pybind(833-834)_to_pybind(989-990)_to_pybind(999-1000)_to_pybind(1009-1010)_to_pybind(1031-1036)_to_pybind(1051-1058)_to_pybind(1115-1128)_to_pybind(1170-1173)_to_pybind(1285-1302)_to_pybind(1358-1364)_to_pybind(1382-1385)
🔇 Additional comments (5)
tensorrt_llm/_torch/pyexecutor/py_executor.py (1)
35-35: Import relocation to llmapi looks correct.Using PeftCacheConfig from tensorrt_llm.llmapi.llm_args aligns with the new config flow; no behavior change here.
tensorrt_llm/_torch/pyexecutor/py_executor_creator.py (2)
16-17: Import reshuffle LGTM.CapacitySchedulerPolicy moved to llmapi; ContextChunkingPolicy/GuidedDecodingConfig remain in bindings. Consistent with the new conversion points.
Also applies to: 19-20
221-223: Deep copy of peft_cache_config is a good containment measure.Prevents accidental mutation of llm_args while still allowing local adjustments.
tensorrt_llm/_torch/pyexecutor/_util.py (2)
14-16: Importing PeftCacheConfig/SchedulerConfig from llmapi is correct.Matches the new public configuration flow.
663-665: PEFT config construction and conversion look good.Using a model instance and calling _to_pybind() at the call site isolates pybind usage and keeps llm_args clean.
Also applies to: 681-681
leslie-fang25
force-pushed
the
leslie/refine_scheduler_config_and_peft_cache_config
branch
from
2d772eb to
4a993cc
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #21827 [ run ] triggered by Bot. Commit: |
|
PR_Github #21827 [ run ] completed with state |
|
/bot run |
|
/bot run --disable-fail-fast |
|
/bot run --disable-fail-fast |
|
PR_Github #21881 [ run ] triggered by Bot. Commit: |
|
PR_Github #21881 [ run ] completed with state |
|
/bot run |
… create_py_executor Signed-off-by: leslie-fang25 <leslief@nvidia.com>
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
|
PR_Github #21962 [ run ] triggered by Bot. Commit: |
leslie-fang25
force-pushed
the
leslie/refine_scheduler_config_and_peft_cache_config
branch
from
a6325ae to
be3d092
Compare
|
/bot run --disable-fail-fast |
|
Hi @suyoggupta @lucaslie, please kindly help to take a look of this change. Thanks. |
|
PR_Github #21968 [ run ] triggered by Bot. Commit: |
|
PR_Github #21962 [ run ] completed with state |
|
PR_Github #21968 [ run ] completed with state |
|
/bot run |
|
PR_Github #22006 [ run ] triggered by Bot. Commit: |
|
PR_Github #22006 [ run ] completed with state |
… create_py_executor (NVIDIA#8451) Signed-off-by: leslie-fang25 <leslief@nvidia.com> Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>
… create_py_executor (NVIDIA#8451) Signed-off-by: leslie-fang25 <leslief@nvidia.com>
… create_py_executor (NVIDIA#8451) Signed-off-by: leslie-fang25 <leslief@nvidia.com>
… create_py_executor (NVIDIA#8451) Signed-off-by: leslie-fang25 <leslief@nvidia.com>
… create_py_executor (NVIDIA#8451) Signed-off-by: leslie-fang25 <leslief@nvidia.com>
4 participants
Summary by CodeRabbit
Release Notes
Description
Limit the scope of pybind configs as of
scheduler_configandpeft_cache_configTest 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.