[None][fix] Update to pull LLM from a central location. #6458
Conversation
📝 WalkthroughWalkthroughA new factory function, Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant BenchmarkScript
participant get_llm
participant LLMClass
User->>BenchmarkScript: Run benchmark (low_latency or throughput)
BenchmarkScript->>get_llm: get_llm(runtime_config, kwargs)
get_llm->>LLMClass: Instantiate appropriate LLM (TensorRT, PyTorch, or AutoDeploy)
get_llm-->>BenchmarkScript: Return LLM instance
BenchmarkScript->>LLMClass: Use LLM instance for benchmarking
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~18 minutes Possibly related PRs
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 as they are similar to previous 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
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 comments)
Other keywords and placeholders
Documentation and Community
|
coderabbitai
bot
requested review from
Superjomn,
chzblych,
kaiyux and
yilin-void
|
/bot run |
![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
🔭 Outside diff range comments (1)
tensorrt_llm/bench/benchmark/__init__.py (1)
1-32: Missing NVIDIA copyright header.According to the coding guidelines, all TensorRT-LLM source files must contain an NVIDIA copyright header.
Add the copyright header at the beginning of the file:
# Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
🧹 Nitpick comments (1)
tensorrt_llm/bench/benchmark/__init__.py (1)
19-31: Consider adding type hints and docstring for better documentation.Adding type hints and a docstring would improve code maintainability and self-documentation.
Apply this enhancement:
-def get_llm(runtime_config: RuntimeConfig, kwargs: dict): +def get_llm(runtime_config: RuntimeConfig, kwargs: dict) -> LLM: + """Create and return an appropriate LLM instance based on the backend configuration. + + Args: + runtime_config: Runtime configuration containing backend selection and settings. + kwargs: Additional keyword arguments to pass to the LLM constructor. + + Returns: + An instance of the appropriate LLM class for the specified backend. + """ llm_cls = LLM
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
tensorrt_llm/bench/benchmark/__init__.py(1 hunks)tensorrt_llm/bench/benchmark/low_latency.py(2 hunks)tensorrt_llm/bench/benchmark/throughput.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 class in the constructor in Python.
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 classes and functions in Python, 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.pytensorrt_llm/bench/benchmark/throughput.pytensorrt_llm/bench/benchmark/__init__.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:
tensorrt_llm/bench/benchmark/low_latency.pytensorrt_llm/bench/benchmark/throughput.pytensorrt_llm/bench/benchmark/__init__.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.
tensorrt_llm/bench/benchmark/low_latency.py (2)
Learnt from: moraxu
PR: #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: yechank-nvidia
PR: #6254
File: tensorrt_llm/_torch/pyexecutor/model_engine.py:1201-1204
Timestamp: 2025-07-22T09:22:14.726Z
Learning: In TensorRT-LLM's multimodal processing pipeline, shared tensor recovery using from_shared_tensor() is only needed during the context phase. Generation requests reuse the already-recovered tensor data and only need to call strip_for_generation() to remove unnecessary multimodal data while preserving the recovered tensors. This avoids redundant tensor recovery operations during generation.
tensorrt_llm/bench/benchmark/throughput.py (3)
Learnt from: moraxu
PR: #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: yechank-nvidia
PR: #6254
File: tensorrt_llm/_torch/pyexecutor/model_engine.py:1201-1204
Timestamp: 2025-07-22T09:22:14.726Z
Learning: In TensorRT-LLM's multimodal processing pipeline, shared tensor recovery using from_shared_tensor() is only needed during the context phase. Generation requests reuse the already-recovered tensor data and only need to call strip_for_generation() to remove unnecessary multimodal data while preserving the recovered tensors. This avoids redundant tensor recovery operations during generation.
Learnt from: CR
PR: NVIDIA/TensorRT-LLM#0
File: CODING_GUIDELINES.md:0-0
Timestamp: 2025-07-29T08:25:52.877Z
Learning: Applies to **/*.py : The code developed for TensorRT-LLM should conform to Python 3.8+.
tensorrt_llm/bench/benchmark/__init__.py (3)
Learnt from: moraxu
PR: #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: yechank-nvidia
PR: #6254
File: tensorrt_llm/_torch/pyexecutor/model_engine.py:1201-1204
Timestamp: 2025-07-22T09:22:14.726Z
Learning: In TensorRT-LLM's multimodal processing pipeline, shared tensor recovery using from_shared_tensor() is only needed during the context phase. Generation requests reuse the already-recovered tensor data and only need to call strip_for_generation() to remove unnecessary multimodal data while preserving the recovered tensors. This avoids redundant tensor recovery operations during generation.
Learnt from: CR
PR: NVIDIA/TensorRT-LLM#0
File: CODING_GUIDELINES.md:0-0
Timestamp: 2025-07-29T08:25:52.877Z
Learning: Applies to **/*.py : The code developed for TensorRT-LLM should conform to Python 3.8+.
⏰ 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 (4)
tensorrt_llm/bench/benchmark/low_latency.py (2)
14-14: LGTM!The import change correctly replaces individual LLM class imports with the centralized factory function.
296-296: Clean refactoring to use centralized LLM instantiation.The direct call to
get_llmproperly replaces the backend-specific instantiation logic, improving maintainability and consistency.tensorrt_llm/bench/benchmark/throughput.py (2)
12-12: LGTM!Import change is consistent with the centralization approach implemented in low_latency.py.
376-376: Consistent implementation of centralized LLM instantiation.The refactoring properly removes backend-specific logic and uses the factory function, maintaining consistency with low_latency.py.
|
/bot kill |
|
PR_Github #13412 [ run ] triggered by Bot |
|
PR_Github #13413 [ kill ] triggered by Bot |
|
PR_Github #13412 [ run ] completed with state |
|
PR_Github #13413 [ kill ] completed with state |
FrankD412
force-pushed
the
fdinatale/trtllm-bench/update_low_trt_opts
branch
from
7e303ec to
9dbd17a
Compare
|
/bot run |
|
PR_Github #13416 [ run ] triggered by Bot |
FrankD412
force-pushed
the
fdinatale/trtllm-bench/update_low_trt_opts
branch
from
955f2a0 to
010de7b
Compare
|
/bot kill |
|
/bot run |
|
PR_Github #13425 [ kill ] triggered by Bot |
|
PR_Github #13416 [ run ] completed with state |
|
PR_Github #13426 [ run ] triggered by Bot |
|
PR_Github #13425 [ kill ] completed with state |
|
/bot kill |
|
PR_Github #13427 [ kill ] triggered by Bot |
|
PR_Github #13426 [ run ] completed with state |
|
PR_Github #13427 [ kill ] completed with state |
|
/bot run |
|
/bot kill |
|
/bot run |
|
PR_Github #16238 [ kill ] triggered by Bot |
|
PR_Github #16227 [ run ] completed with state |
|
PR_Github #16238 [ kill ] completed with state |
|
PR_Github #16239 [ run ] triggered by Bot |
|
PR_Github #16239 [ run ] completed with state |
|
/bot run |
|
PR_Github #16245 [ run ] triggered by Bot |
|
/bot kill |
|
PR_Github #16246 [ kill ] triggered by Bot |
|
PR_Github #16245 [ run ] completed with state |
|
PR_Github #16246 [ kill ] completed with state |
|
/bot run |
|
PR_Github #16248 [ run ] triggered by Bot |
|
PR_Github #16248 [ run ] completed with state |
|
/bot run |
|
PR_Github #16369 [ run ] triggered by Bot |
|
PR_Github #16369 [ run ] completed with state |
|
/bot run --stage-list "B200_PCIe-PyTorch-2" |
|
PR_Github #16464 [ run ] triggered by Bot |
|
PR_Github #16464 [ run ] completed with state |
|
/bot skip --comment "All tests have passed between pipelines 12369 and 12298" |
|
PR_Github #16471 [ skip ] triggered by Bot |
|
PR_Github #16471 [ skip ] completed with state |
5 participants
Summary by CodeRabbit
Description
This PR moves the LLM initialization to a single location to try and minimize the drift between the throughput and latency benchmarks as the throughput benchmark gets updated without updating the latency benchmark.
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.