[TRTLLM-8070][test] add generation logits case for llama3 #7759
Conversation
crazydemo
force-pushed
the
add_test_case
branch
from
f15027b to
d819af2
Compare
|
/bot run |
📝 WalkthroughWalkthroughAdds a new parameterized async integration test (test_llmapi_generation_logits) to exercise LLM generate_async with optional generation logits and streaming for Llama models. Updates the QA test list with four corresponding entries. The new test block appears twice in the same file. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant T as Test (pytest)
participant L as LLM (tensorrt_llm.LLM)
participant E as Event Loop
participant S as Stream (async iterator)
rect rgb(245,248,255)
note right of T: Parametrize: model_path, return_generation_logits
T->>L: Construct LLM(tp_size, model_path)
T->>L: Configure SamplingParams(seq_len, max_tokens, return_generation_logits)
end
rect rgb(245,255,245)
T->>E: run(async_generate())
activate E
E->>L: generate_async(prompt_ids, stream=True)
L-->>S: return async stream
loop stream tokens/chunks
S-->>E: yield output chunk (+optional logits)
E-->>T: collect outputs
end
E-->>T: finalize results
deactivate E
end
rect rgb(255,248,245)
T->>T: assert outputs not empty
T->>L: shutdown()
end
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes ✨ Finishing touches
🧪 Generate unit tests
Tip 👮 Agentic pre-merge checks are now available in preview!Pro plan users can now enable pre-merge checks in their settings to enforce checklists before merging PRs.
Please see the documentation for more information. Example: reviews:
pre_merge_checks:
custom_checks:
- name: "Undocumented Breaking Changes"
mode: "warning"
instructions: |
Pass/fail criteria: All breaking changes to public APIs, CLI flags, environment variables, configuration keys, database schemas, or HTTP/GraphQL endpoints must be documented in the "Breaking Change" section of the PR description and in CHANGELOG.md. Exclude purely internal or private changes (e.g., code not exported from package entry points or explicitly marked as internal).Please share your feedback with us on this Discord post. 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 Pre-merge checks❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
|
|
PR_Github #18754 [ run ] triggered by Bot |
![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 (5)
tests/integration/defs/test_e2e.py (5)
3248-3248: Remove unused fixture parameterllm_venvRuff flags it (ARG001). It’s not used in this test.
Apply this diff:
-def test_llmapi_generation_logits(llm_venv, model_path, return_generation_logits): +def test_llmapi_generation_logits(model_path, return_generation_logits):
3311-3312: Prefer asyncio.run to manage the event loopAvoids reuse of a possibly closed loop and is cleaner in pytest.
Apply this diff:
- loop = asyncio.get_event_loop() - loop.run_until_complete(async_generation_test()) + asyncio.run(async_generation_test())
3256-3260: Right-size seq_len/max_tokens to keep CI stable131072/100000 can be excessive and flaky in CI even with memory skips. Smaller bounds still exercise the path.
Apply this diff:
- seq_len, max_tokens = 131072, 100000 + seq_len, max_tokens = 4096, 64 if return_generation_logits: - # use short seq_len and max_tokens for testing when return_generation_logits is True - seq_len, max_tokens = 1024, 1000 + # keep logits case short to cap tensor sizes + seq_len, max_tokens = 1024, 64
3263-3276: Trim unused/odd options in params (batch size, guided decoding)
- cuda_graph batch_sizes=512 doesn’t match batch=1 here; set to 1.
- guided_decoding_backend is unused; drop to avoid unnecessary deps.
Apply this diff:
- "cuda_graph_config": { - "batch_sizes": [512] - }, - "enable_chunked_prefill": True, - "guided_decoding_backend": "xgrammar", + "cuda_graph_config": {"batch_sizes": [1]}, + "enable_chunked_prefill": True,
3291-3309: Use context manager for LLM lifecycleSimplifies cleanup and avoids manual shutdown logic.
Apply this diff:
- llm = LLM(**params, model=model_path_full, tokenizer=model_path_full) - - try: - outputs = [] - async for output in llm.generate_async( - prompt, - sampling_params, - streaming=True, - ): - outputs.append(output) - print(f"Generated: {output}") - - # Verify that we got some output - assert len(outputs) > 0, "No output generated" - print(f"Successfully generated {len(outputs)} streaming outputs") - - finally: - llm.shutdown() + outputs = [] + with LLM(**params, model=model_path_full, tokenizer=model_path_full) as llm: + async for output in llm.generate_async( + prompt, + sampling_params, + streaming=True, + ): + outputs.append(output) + print(f"Generated: {output}") + + # Verify that we got some output + assert len(outputs) > 0, "No output generated" + print(f"Successfully generated {len(outputs)} streaming outputs")
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
tests/integration/defs/test_e2e.py(1 hunks)tests/integration/test_lists/qa/llm_function_nim.txt(1 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:
tests/integration/defs/test_e2e.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:
tests/integration/defs/test_e2e.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:
tests/integration/defs/test_e2e.py
🧠 Learnings (5)
📓 Common learnings
Learnt from: fredricz-20070104
PR: NVIDIA/TensorRT-LLM#7645
File: tests/integration/test_lists/qa/llm_function_core.txt:648-648
Timestamp: 2025-09-09T09:40:45.658Z
Learning: In TensorRT-LLM test lists, it's common and intentional for the same test to appear in multiple test list files when they serve different purposes (e.g., llm_function_core.txt for comprehensive core functionality testing and llm_function_core_sanity.txt for quick sanity checks). This duplication allows tests to be run in different testing contexts.
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.
📚 Learning: 2025-09-09T09:40:45.658Z
Learnt from: fredricz-20070104
PR: NVIDIA/TensorRT-LLM#7645
File: tests/integration/test_lists/qa/llm_function_core.txt:648-648
Timestamp: 2025-09-09T09:40:45.658Z
Learning: In TensorRT-LLM test lists, it's common and intentional for the same test to appear in multiple test list files when they serve different purposes (e.g., llm_function_core.txt for comprehensive core functionality testing and llm_function_core_sanity.txt for quick sanity checks). This duplication allows tests to be run in different testing contexts.
Applied to files:
tests/integration/test_lists/qa/llm_function_nim.txt
📚 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/test_lists/qa/llm_function_nim.txttests/integration/defs/test_e2e.py
📚 Learning: 2025-08-26T09:49:04.956Z
Learnt from: pengbowang-nv
PR: NVIDIA/TensorRT-LLM#7192
File: tests/integration/test_lists/test-db/l0_dgx_b200.yml:56-72
Timestamp: 2025-08-26T09:49:04.956Z
Learning: In TensorRT-LLM test configuration files, the test scheduling system handles wildcard matching with special rules that prevent duplicate test execution even when the same tests appear in multiple yaml files with overlapping GPU wildcards (e.g., "*b200*" and "*gb200*").
Applied to files:
tests/integration/test_lists/qa/llm_function_nim.txt
📚 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/test_lists/qa/llm_function_nim.txt
🧬 Code graph analysis (1)
tests/integration/defs/test_e2e.py (3)
tests/integration/defs/conftest.py (1)
llm_models_root(77-82)tensorrt_llm/llmapi/llm.py (6)
LLM(1022-1038)prompt(81-82)tokenizer(700-704)tokenizer(707-708)generate_async(319-459)shutdown(711-718)tensorrt_llm/sampling_params.py (1)
SamplingParams(125-486)
🪛 Ruff (0.12.2)
tests/integration/defs/test_e2e.py
3248-3248: Unused function argument: llm_venv
(ARG001)
⏰ 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 (1)
tests/integration/test_lists/qa/llm_function_nim.txt (1)
175-178: LGTM: test entries wired into NIM list correctlyThe four parametrized cases map 1:1 to the new test and follow existing naming. No duplication concerns.
|
PR_Github #18754 [ run ] completed with state |
crazydemo
force-pushed
the
add_test_case
branch
from
d819af2 to
920f318
Compare
|
/bot run |
|
PR_Github #18865 [ run ] triggered by Bot |
|
/bot kill |
crazydemo
force-pushed
the
add_test_case
branch
from
920f318 to
0fdab58
Compare
|
PR_Github #18866 [ kill ] triggered by Bot |
|
PR_Github #18865 [ run ] completed with state |
|
PR_Github #18866 [ kill ] completed with state |
|
/bot run |
|
PR_Github #18869 [ run ] triggered by Bot |
|
PR_Github #18869 [ run ] completed with state |
crazydemo
force-pushed
the
add_test_case
branch
from
0fdab58 to
5d95efa
Compare
|
/bot run |
|
PR_Github #18897 [ run ] triggered by Bot |
|
PR_Github #18897 [ run ] completed with state |
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
crazydemo
force-pushed
the
add_test_case
branch
from
5d95efa to
efddb82
Compare
|
/bot run |
|
PR_Github #19069 [ run ] triggered by Bot |
|
PR_Github #19069 [ run ] completed with state |
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
3 participants
These cases can pass locally on 8xA100
Summary by CodeRabbit
Description
Test 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.
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.