[None][infra] Enable test of chunked prefill with logit post processor #6483
Conversation
📝 WalkthroughWalkthroughThe changes update documentation to indicate support for chunked prefill in the logits post processor, and enhance test coverage by parameterizing the relevant unit test to run with and without chunked prefill enabled. The test harness is updated to dynamically adjust prompts and token limits based on the chunked prefill setting. Changes
Sequence Diagram(s)sequenceDiagram
participant Tester
participant TestHarness
participant LLMTestHarness
Tester->>TestHarness: Call tinyllama_logits_processor_test_harness(enable_chunked_prefill)
alt enable_chunked_prefill is True
TestHarness->>TestHarness: Repeat first prompt 256 times
TestHarness->>TestHarness: Set max_num_tokens = 256
else enable_chunked_prefill is False
TestHarness->>TestHarness: Use original prompts
end
TestHarness->>LLMTestHarness: Call llm_test_harness with adjusted prompts and kwargs
Estimated code review effort🎯 2 (Simple) | ⏱️ ~7 minutes Suggested labels
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 (3)
🚧 Files skipped from review as they are similar to previous changes (3)
⏰ 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. 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
|
|
/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: 0
🧹 Nitpick comments (2)
tests/unittest/llmapi/test_llm.py (1)
1061-1064: Avoid potential mutation of the original prompts list.The current implementation assigns
promptstoinput_promptsand then modifiesinput_prompts[0], which could potentially mutate the originalpromptslist if it's mutable.Apply this diff to create a copy and avoid potential side effects:
- input_prompts = prompts - if llm_kwargs.get('enable_chunked_prefill', None): - input_prompts[0] = input_prompts[0] * 256 - llm_kwargs["max_num_tokens"] = 256 + input_prompts = prompts.copy() + if llm_kwargs.get('enable_chunked_prefill', None): + input_prompts[0] = input_prompts[0] * 256 + llm_kwargs["max_num_tokens"] = 256tests/unittest/llmapi/test_llm_pytorch.py (1)
36-36: Minor style note: trailing comma in parametrize.The trailing comma after
Truein the parametrize decorator is valid Python syntax but could be removed for consistency, though it's not a functional issue.-@pytest.mark.parametrize("enable_chunked_prefill,", [False, True,]) +@pytest.mark.parametrize("enable_chunked_prefill", [False, True])
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
docs/source/torch/features/feature_combination_matrix.md(1 hunks)tests/unittest/llmapi/test_llm.py(1 hunks)tests/unittest/llmapi/test_llm_pytorch.py(1 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 reflection.
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/unittest/llmapi/test_llm_pytorch.pytests/unittest/llmapi/test_llm.py
**/*.{cpp,h,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/unittest/llmapi/test_llm_pytorch.pytests/unittest/llmapi/test_llm.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.
docs/source/torch/features/feature_combination_matrix.md (1)
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.
tests/unittest/llmapi/test_llm_pytorch.py (1)
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.
tests/unittest/llmapi/test_llm.py (1)
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.
🔇 Additional comments (3)
docs/source/torch/features/feature_combination_matrix.md (1)
17-17: LGTM! Documentation accurately reflects the new feature support.The update correctly changes the status from "Untested" to "Yes" for the Logits Post Processor + Chunked Prefill combination, which aligns with the PR's objective to enable testing of this feature combination.
tests/unittest/llmapi/test_llm.py (1)
1055-1073: LGTM! Well-implemented chunked prefill test support.The logic correctly enables the test harness to handle both regular and chunked prefill scenarios by:
- Creating longer input sequences (256x repetition) to trigger chunked prefill behavior
- Adjusting the max token limit appropriately
- Maintaining backward compatibility for non-chunked prefill tests
This enables comprehensive testing of the logits processor with chunked prefill functionality.
tests/unittest/llmapi/test_llm_pytorch.py (1)
36-38: LGTM! Good test coverage approach.The parametrization correctly enables testing both chunked and non-chunked prefill modes, providing comprehensive coverage for the logits processor functionality. The function call properly passes the parameter to the test harness.
|
PR_Github #13524 [ run ] triggered by Bot |
|
/bot run |
|
PR_Github #13525 [ run ] triggered by Bot |
|
PR_Github #13524 [ run ] completed with state |
|
PR_Github #13525 [ run ] completed with state |
leslie-fang25
force-pushed
the
leslie/chunked_prefill_logit_post_processor
branch
from
9502dd9 to
0e2d5eb
Compare
|
/bot run |
|
PR_Github #13590 [ run ] triggered by Bot |
|
PR_Github #13590 [ run ] completed with state |
|
/bot run |
|
PR_Github #13860 [ run ] triggered by Bot |
|
PR_Github #13860 [ run ] completed with state |
leslie-fang25
force-pushed
the
leslie/chunked_prefill_logit_post_processor
branch
from
6aa73e3 to
c6b245c
Compare
|
/bot run |
leslie-fang25
changed the title
|
PR_Github #13866 [ run ] triggered by Bot |
|
PR_Github #13866 [ run ] completed with state |
|
/bot run |
|
PR_Github #13868 [ run ] triggered by Bot |
|
PR_Github #13868 [ run ] completed with state |
Signed-off-by: leslie-fang25 <[email protected]>
Signed-off-by: leslie-fang25 <[email protected]>
Signed-off-by: leslie-fang25 <[email protected]>
nv-guomingz
force-pushed
the
leslie/chunked_prefill_logit_post_processor
branch
from
c6b245c to
b7c828c
Compare
|
/bot reuse-pipeline |
|
PR_Github #13929 [ reuse-pipeline ] triggered by Bot |
|
PR_Github #13929 [ reuse-pipeline ] completed with state |
NVIDIA#6483) Signed-off-by: leslie-fang25 <[email protected]> Signed-off-by: Lanyu Liao <[email protected]>
NVIDIA#6483) Signed-off-by: leslie-fang25 <[email protected]>
4 participants
Summary by CodeRabbit
Documentation
Tests
Description
This diff enables test of chunked prefill with logit post processor.
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.