[None][test] cherry-pick: correct test-db context for perf yaml file and add mistral cases #6688
Conversation
📝 WalkthroughWalkthroughA new model entry for "mistral_small_v3.1_24b" was added to the performance test model dictionary. Performance test YAMLs were updated to include new test cases for this model across single, dual, and multi-GPU scenarios. Several test suite and group names were also renamed for consistency, with no changes to test logic. Changes
Sequence Diagram(s)sequenceDiagram
participant TestRunner
participant TestYAML
participant PerfTestScript
participant ModelRegistry
TestRunner->>TestYAML: Load test suite (llm_perf_full/cluster/...)
TestYAML->>TestRunner: Provide test cases (including mistral_small_v3.1_24b)
TestRunner->>PerfTestScript: Run test_perf.py with model key
PerfTestScript->>ModelRegistry: Lookup MODEL_PATH_DICT for mistral_small_v3.1_24b
ModelRegistry-->>PerfTestScript: Return model path
PerfTestScript->>TestRunner: Execute performance test and report results
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 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 (6)
✅ Files skipped from review due to trivial changes (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. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
ruodil
changed the title
![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)
tests/integration/test_lists/qa/llm_perf_cluster.yml (1)
45-49: Model-path entry & TIMEOUT style – please validate.
mistral_small_v3.1_24bmust exist inMODEL_PATH_DICT(looks added in the PR, but a verify pass prevents silent typos).- Most lines in this file use
TIMEOUT(120), yet some legacy entries showTIMEOUT (120)(extra space). Stick to one pattern to avoid fragile string parsing in tooling.tests/integration/test_lists/qa/llm_perf_full.yml (2)
52-56: Minor formatting nit – keep comment style consistent.
#Mistral-Small-3.1-24B-Instruct-2503lacks a space after#, whereas neighbouring comment blocks include one (# Phi-4-…). Uniform formatting simplifies automated docs generation.-#Mistral-Small-3.1-24B-Instruct-2503 +# Mistral-Small-3.1-24B-Instruct-2503
52-56: Double-check TIMEOUT annotation consistency.The newly added entries use
TIMEOUT(120)– good. Elsewhere in this same YAML (llama_v4_scout_*etc.) we still haveTIMEOUT (100)(space). If downstream parsers trim spaces you’re fine; if they don’t, normalise now.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (6)
tests/integration/defs/perf/test_perf.py(1 hunks)tests/integration/test_lists/qa/llm_perf_cluster.yml(3 hunks)tests/integration/test_lists/qa/llm_perf_full.yml(3 hunks)tests/integration/test_lists/qa/llm_perf_sanity.yml(1 hunks)tests/integration/test_lists/qa/llm_trt_integration_perf.yml(1 hunks)tests/integration/test_lists/qa/llm_trt_integration_perf_sanity.yml(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
**/*.py: Python code 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 Python file, prefer docstrings over comments.
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 class docstring.
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:
tests/integration/defs/perf/test_perf.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:
tests/integration/defs/perf/test_perf.py
🧠 Learnings (6)
📓 Common learnings
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.
Learnt from: venkywonka
PR: NVIDIA/TensorRT-LLM#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".
Learnt from: venkywonka
PR: NVIDIA/TensorRT-LLM#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".
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: in tensorrt-llm testing, it's common to have both cli flow tests (test_cli_flow.py) and pytorch api ...
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_perf_cluster.ymltests/integration/test_lists/qa/llm_trt_integration_perf.ymltests/integration/test_lists/qa/llm_trt_integration_perf_sanity.ymltests/integration/test_lists/qa/llm_perf_full.ymltests/integration/test_lists/qa/llm_perf_sanity.yml
📚 Learning: in tensorrt-llm, test files (files under tests/ directories) do not require nvidia copyright headers...
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_perf_cluster.ymltests/integration/test_lists/qa/llm_trt_integration_perf.ymltests/integration/test_lists/qa/llm_trt_integration_perf_sanity.ymltests/integration/test_lists/qa/llm_perf_full.ymltests/integration/test_lists/qa/llm_perf_sanity.yml
📚 Learning: ministral is a valid model name from mistral ai, distinct from the regular mistral models. in tensor...
Learnt from: venkywonka
PR: NVIDIA/TensorRT-LLM#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/test_lists/qa/llm_perf_cluster.ymltests/integration/defs/perf/test_perf.pytests/integration/test_lists/qa/llm_perf_full.yml
📚 Learning: ministral is a valid and distinct model family from mistral ai, separate from their regular mistral ...
Learnt from: venkywonka
PR: NVIDIA/TensorRT-LLM#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/test_lists/qa/llm_perf_cluster.ymltests/integration/defs/perf/test_perf.pytests/integration/test_lists/qa/llm_perf_full.yml
📚 Learning: in tensorrt-llm, examples directory can have different dependency versions than the root requirement...
Learnt from: yibinl-nvidia
PR: NVIDIA/TensorRT-LLM#6506
File: examples/models/core/mixtral/requirements.txt:3-3
Timestamp: 2025-08-01T15:14:45.673Z
Learning: In TensorRT-LLM, examples directory can have different dependency versions than the root requirements.txt file. Version conflicts between root and examples dependencies are acceptable because examples are designed to be standalone and self-contained.
Applied to files:
tests/integration/test_lists/qa/llm_perf_cluster.ymltests/integration/test_lists/qa/llm_trt_integration_perf.ymltests/integration/test_lists/qa/llm_trt_integration_perf_sanity.ymltests/integration/test_lists/qa/llm_perf_full.ymltests/integration/test_lists/qa/llm_perf_sanity.yml
⏰ 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 (7)
tests/integration/test_lists/qa/llm_perf_cluster.yml (2)
65-69: Stress parameters look extreme for 2×GPU – sanity check memory/latency.
maxbs:4096-maxnt:20000pluscon:200on merely two GPUs is very heavy and will OOM on 80 GB H100s unless KV & activation compression are engaged. Make sure:
- The perf harness enables paged KV or low-mem optimisations.
- Jenkins timeout (120 s) is realistically reachable; otherwise orchestrator will fail the whole stage.
2-2: No hard-coded references totrt_llm_release_perf_cluster_testfound—please verify external automation
A grep over the repo returned no occurrences of the old suite name. From the codebase side you’re all set, but double-check that:
- Jenkins jobs, internal runners or any external scripts consuming this YAML have been updated to use
llm_perf_clusterinstead oftrt_llm_release_perf_cluster_test.tests/integration/test_lists/qa/llm_perf_full.yml (2)
2-2: Root key renamed – mirror the change everywhere.
llm_perf_fullsupersedestrt_llm_release_perf_test. Ensure:
- The CI job that assembles the “full” matrix loads this new key.
- The validator script in
test_list_validation.pyknows the new canonical name.
139-143: Extreme batch / sequence lengths – verify that the test really runs.
maxbs:4096-maxnt:20000withcon:200on two GPUs will allocate >2 TiB KV cache in FP16 unless KV compression is used. Validate that:
kv_fracorkv_cache_dtypeknobs are implicitly applied.- Per-GPU memory assumption matches available hardware in CI.
If not, gate this test behind higher GPU-memory criteria or reduce parameters.
tests/integration/test_lists/qa/llm_trt_integration_perf.yml (1)
2-2: Confirm downstream tooling is updated to the new suite key.The root-level key was renamed to
llm_trt_integration_perf. Double-check that:
- Jenkins / tox jobs referencing the previous name (
trt_llm_integration_perf_test) have been updated.- Any helper scripts that grep for the old key (e.g., test-list validators) have corresponding changes.
A silent mismatch will cause the whole list to be skipped at dispatch time.
tests/integration/test_lists/qa/llm_trt_integration_perf_sanity.yml (1)
2-2: Verify the sanity list rename is reflected in CI filters.
trt_llm_integration_perf_sanity_test→llm_trt_integration_perf_sanitymirrors the full perf list rename, but the CI “quick-sanity” jobs are usually hard-coded. Make sure the corresponding job definitions (e.g.,qa-sanity-perf) use the new identifier, otherwise no tests will run.tests/integration/test_lists/qa/llm_perf_sanity.yml (1)
2-2: Cross-check updated key with all consumers.The umbrella key is now
llm_perf_sanity. Confirm:
tests/integration/tools/collect_perf_lists.py(or equivalent) includes the new label.- Any documentation or dashboards that pivot on the old
trt_llm_release_perf_sanity_teststring are updated.No content change is needed here; this is purely a naming contract.
|
/bot skip --comment"skip test as only add cases" |
ruodil
force-pushed
the
user/ruodil/release1.0
branch
from
454003e to
c3e4a26
Compare
|
PR_Github #14447 Bot args parsing error: usage: /bot skip --comment COMMENT |
|
/bot skip --comment "skip test as only add cases" |
Signed-off-by: ruodil <[email protected]>
Signed-off-by: ruodil <[email protected]>
|
PR_Github #14450 [ skip ] triggered by Bot |
|
PR_Github #14450 [ skip ] completed with state |
…and add mistral cases (NVIDIA#6688) Signed-off-by: ruodil <[email protected]>
…and add mistral cases (NVIDIA#6688) Signed-off-by: ruodil <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…and add mistral cases (NVIDIA#6688) Signed-off-by: ruodil <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…and add mistral cases (NVIDIA#6688) Signed-off-by: ruodil <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
3 participants
Summary by CodeRabbit
New Features
Tests
Description
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.
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.