[https://nvbugs/5669097][tests] Add MMMU test for mistral small #10530
Conversation
|
/bot run |
📝 WalkthroughWalkthroughThese changes add test support for the Mistral-Small-3.1-24B-Instruct model by introducing accuracy benchmark data, a new test harness class with specific sampling and memory configurations, adjusting end-to-end test validation logic, and updating test waivers. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes 🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
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: 0
🧹 Nitpick comments (1)
tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.py (1)
319-340: RenameSAMPLING_PARAMStosampling_paramsfor consistency.The class-level variable is named
SAMPLING_PARAMS(uppercase), which is inconsistent with all other test classes in this file that usesampling_params(lowercase). For maintainability and consistency, please use the established naming convention.♻️ Proposed refactor for naming consistency
- # NOTE: MMMU adds <|endoftext|> to the stop token. - SAMPLING_PARAMS = SamplingParams( + # NOTE: MMMU adds <|endoftext|> to the stop token. + sampling_params = SamplingParams( max_tokens=MMMU.MAX_OUTPUT_LEN, truncate_prompt_tokens=MMMU.MAX_INPUT_LEN, stop="<|endoftext|>", ) @pytest.mark.skip_less_device_memory(80000) def test_auto_dtype(self): kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.75) with LLM( self.MODEL_PATH, kv_cache_config=kv_cache_config, enable_chunked_prefill=True ) as llm: task = MMMU(self.MODEL_NAME) - task.evaluate(llm, sampling_params=self.SAMPLING_PARAMS) + task.evaluate(llm, sampling_params=self.sampling_params)
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
tests/integration/defs/accuracy/references/mmmu.yamltests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.pytests/integration/defs/test_e2e.pytests/integration/test_lists/waives.txt
💤 Files with no reviewable changes (1)
- tests/integration/test_lists/waives.txt
🧰 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 Python modules, 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, with prefixkfor variable names that start with a number (e.g.,k_99th_percentile)
Python global variables should use upper snake_case with prefixG(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 Python interfaces that may be used outside a file, prefer docstrings over comments
Use comments in Python 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
Python attributes and variables can be documented inline with the format"""<type>: Description"""
Avoid using reflection in Python when functionality can be easily achieved without reflection
When using try-except blocks in Python, limit the except clause to the smallest set of errors possible
When using try-except blocks in Python to handle multiple possible variable types (duck-typing), keep the body of the try as small as possible and use the else block for the main logic
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.pytests/integration/defs/test_e2e.py
**/*.{cpp,cc,cxx,h,hpp,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
All TensorRT-LLM source files (.cpp, .h, .cu, .py, and other source files) should contain an NVIDIA copyright header with the year of latest meaningful modification
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.pytests/integration/defs/test_e2e.py
🧠 Learnings (5)
📓 Common learnings
Learnt from: venkywonka
Repo: NVIDIA/TensorRT-LLM PR: 6650
File: tests/integration/test_lists/qa/llm_perf_cluster.yml:33-37
Timestamp: 2025-08-06T03:47:16.802Z
Learning: Ministral is a valid and distinct model family from Mistral AI, separate from their regular Mistral models. Ministral 8B is specifically designed for edge computing and on-device applications, released in October 2024. In TensorRT-LLM test configurations, "ministral_8b" and "ministral_8b_fp8" are correct model identifiers and should not be changed to "mistral_8b".
📚 Learning: 2025-08-06T03:47:16.802Z
Learnt from: venkywonka
Repo: NVIDIA/TensorRT-LLM PR: 6650
File: tests/integration/test_lists/qa/llm_perf_cluster.yml:33-37
Timestamp: 2025-08-06T03:47:16.802Z
Learning: Ministral is a valid model name from Mistral AI, distinct from the regular Mistral models. In TensorRT-LLM test configurations, "ministral_8b" and "ministral_8b_fp8" are correct model identifiers and should not be changed to "mistral_8b".
Applied to files:
tests/integration/defs/accuracy/references/mmmu.yaml
📚 Learning: 2025-08-06T03:47:16.802Z
Learnt from: venkywonka
Repo: NVIDIA/TensorRT-LLM PR: 6650
File: tests/integration/test_lists/qa/llm_perf_cluster.yml:33-37
Timestamp: 2025-08-06T03:47:16.802Z
Learning: Ministral is a valid and distinct model family from Mistral AI, separate from their regular Mistral models. Ministral 8B is specifically designed for edge computing and on-device applications, released in October 2024. In TensorRT-LLM test configurations, "ministral_8b" and "ministral_8b_fp8" are correct model identifiers and should not be changed to "mistral_8b".
Applied to files:
tests/integration/defs/accuracy/references/mmmu.yaml
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
Repo: NVIDIA/TensorRT-LLM 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.
Applied to files:
tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.py
📚 Learning: 2025-09-09T09:40:45.658Z
Learnt from: fredricz-20070104
Repo: NVIDIA/TensorRT-LLM PR: 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/defs/accuracy/test_llm_api_pytorch_multimodal.py
🧬 Code graph analysis (1)
tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.py (5)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
TestMistralSmall24B(966-993)tests/integration/defs/accuracy/accuracy_core.py (1)
LlmapiAccuracyTestHarness(898-909)tensorrt_llm/sampling_params.py (1)
SamplingParams(113-552)tensorrt_llm/evaluate/lm_eval.py (3)
MMMU(696-749)evaluate(428-463)evaluate(795-849)tensorrt_llm/llmapi/llm_args.py (1)
KvCacheConfig(1598-1742)
⏰ 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 (3)
tests/integration/defs/test_e2e.py (2)
2607-2609: LGTM! Guard clause appropriately handles unsupported modalities.The guard correctly skips tests when a modality is not supported for a specific model, preventing failures from missing test data.
2628-2631: LGTM! Appropriate separation of smoke tests from accuracy tests.Setting
match_ratio = 0.0converts this from an accuracy test to a functional smoke test, which aligns with the PR objectives. The corresponding accuracy testTestMistralSmall24Bhas been added totest_llm_api_pytorch_multimodal.pyas noted in the comment.tests/integration/defs/accuracy/references/mmmu.yaml (1)
29-30: LGTM! Reference accuracy entry correctly added.The new model entry follows the established YAML format and the model name matches the
MODEL_NAMEdefined inTestMistralSmall24B.
|
PR_Github #31000 [ run ] triggered by Bot. Commit: |
tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.py
Outdated
Show resolved
Hide resolved
tests/integration/defs/accuracy/test_llm_api_pytorch_multimodal.py
Outdated
Show resolved
Hide resolved
2ez4bz
force-pushed
the
dev-mistral-small-bugs
branch
from
b080a60 to
ca90a3b
Compare
|
PR_Github #31000 [ run ] completed with state
|
2ez4bz
force-pushed
the
dev-mistral-small-bugs
branch
from
ca90a3b to
f1646ed
Compare
|
/bot run |
|
PR_Github #31105 [ run ] triggered by Bot. Commit: |
|
PR_Github #31105 [ run ] completed with state
|
2ez4bz
force-pushed
the
dev-mistral-small-bugs
branch
from
f1646ed to
6099568
Compare
|
/bot run |
|
PR_Github #31113 [ run ] triggered by Bot. Commit: |
|
PR_Github #31113 [ run ] completed with state
|
yechank-nvidia
added
the
Multimodal
|
/bot run |
|
PR_Github #31192 [ run ] triggered by Bot. Commit: |
|
PR_Github #31192 [ run ] completed with state
|
|
/bot run |
Signed-off-by: William Zhang <[email protected]>
2ez4bz
force-pushed
the
dev-mistral-small-bugs
branch
from
6099568 to
12bac95
Compare
|
/bot run |
|
PR_Github #31281 [ run ] triggered by Bot. Commit: |
|
PR_Github #31281 [ run ] completed with state |
4 participants
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.
Description
This PR adjusts existing keyword matching tests to be functional / smoke tests, and adds an E2E accuracy test (MMMU) for more robustness.
Test Coverage
As described above.
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
Update tava architecture diagram if there is a significant design change in PR.
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.