[#10056][chore] AutoDeploy: Enable the super accuracy test #10171
Conversation
📝 WalkthroughWalkthroughUpdates a model path resolution in a test class to use a dynamic path function and adjusts test registry entries across multiple configuration files to include a new Nemotron Super V3 BF16 test variant while removing older test entries. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes
Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
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: 3
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (4)
tests/integration/defs/accuracy/test_llm_api_autodeploy.py(1 hunks)tests/integration/test_lists/test-db/l0_b200.yml(1 hunks)tests/integration/test_lists/test-db/l0_dgx_h200.yml(1 hunks)tests/integration/test_lists/test-db/l0_h100.yml(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: 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 files should use snake_case naming:some_file.py
Python classes should use PascalCase naming:class SomeClass
Python functions and methods should use snake_case naming:def my_awesome_function():
Python local variables should use snake_case naming:my_variable = ...
Python variable names that start with a number should be prefixed with 'k':k_99th_percentile = ...
Python global variables should use upper snake_case with prefix 'G':G_MY_GLOBAL = ...
Python constants should use upper snake_case naming: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
Python comments should be reserved for code within a function, or interfaces that are local to a file
Use Google style docstrings in Python for classes and functions, which can be parsed by Sphinx
Python attributes and variables can be documented inline with type and description
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 in Python to handle multiple possible variable types (duck-typing), keep the body of the try as small as possible, using the else block for logic
Files:
tests/integration/defs/accuracy/test_llm_api_autodeploy.py
**/*.{cpp,h,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the year of its latest meaningful modification
Files:
tests/integration/defs/accuracy/test_llm_api_autodeploy.py
🧠 Learnings (5)
📚 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/test_lists/test-db/l0_b200.ymltests/integration/test_lists/test-db/l0_h100.ymltests/integration/test_lists/test-db/l0_dgx_h200.yml
📚 Learning: 2025-09-17T02:48:52.732Z
Learnt from: tongyuantongyu
Repo: NVIDIA/TensorRT-LLM PR: 7781
File: tests/integration/test_lists/waives.txt:313-313
Timestamp: 2025-09-17T02:48:52.732Z
Learning: In TensorRT-LLM, `tests/integration/test_lists/waives.txt` is specifically for waiving/skipping tests, while other test list files like those in `test-db/` and `qa/` directories are for different test execution contexts (pre-merge, post-merge, QA tests). The same test appearing in both waives.txt and execution list files is intentional - the test is part of test suites but will be skipped due to the waiver.
Applied to files:
tests/integration/test_lists/test-db/l0_b200.yml
📚 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/test_lists/test-db/l0_b200.ymltests/integration/test_lists/test-db/l0_h100.ymltests/integration/defs/accuracy/test_llm_api_autodeploy.py
📚 Learning: 2025-08-26T09:49:04.956Z
Learnt from: pengbowang-nv
Repo: NVIDIA/TensorRT-LLM PR: 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/test-db/l0_b200.ymltests/integration/test_lists/test-db/l0_h100.ymltests/integration/test_lists/test-db/l0_dgx_h200.yml
📚 Learning: 2025-08-06T13:58:07.506Z
Learnt from: galagam
Repo: NVIDIA/TensorRT-LLM PR: 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/defs/accuracy/test_llm_api_autodeploy.py
⏰ 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/defs/accuracy/test_llm_api_autodeploy.py (1)
239-239: Code pattern is consistent with existing model paths.The change from hardcoded path to
f"{llm_models_root()}/Nemotron-Super-3-120B-A12B-dev"follows the established pattern used byTestNemotronHandTestNemotronMOE. The model path is correctly used in thetest_bf16method. No issues found.
| - unittest/_torch/auto_deploy/unit/singlegpu -k "not test_trtllm_bench_backend_comparison" | ||
| - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[False-1] | ||
| - accuracy/test_llm_api_autodeploy.py::TestNemotronMOE::test_fp8 | ||
| - accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_bf16 |
There was a problem hiding this comment.
Verify GPU count requirements match test expectations.
The test is added to a condition block requiring system_gpu_count: gte: 1, lte: 1 (lines 5-7), but the test implementation requires 8 GPUs (marked with @pytest.mark.skip_less_device(8) and world_size=8 in the test definition).
This configuration mismatch will prevent the test from running successfully. The test should either:
- Be moved to a multi-GPU condition block (e.g., one requiring 8 GPUs), or
- Be modified to support single-GPU execution
Based on learnings, the same test appearing in multiple test lists serves different purposes. However, hardware requirements must still match.
🤖 Prompt for AI Agents
In tests/integration/test_lists/test-db/l0_b200.yml around line 97, the test
entry for accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_bf16 is
under a condition block that requires system_gpu_count: gte: 1, lte: 1 but the
test implementation requires 8 GPUs (pytest.mark.skip_less_device(8) and
world_size=8); fix by moving this test entry into a multi-GPU condition block
that requires at least 8 GPUs (e.g., system_gpu_count: gte: 8) or change the
test to run on a single GPU by removing the 8-GPU dependency (remove skip marker
and adjust world_size and test logic) so the YAML hardware requirement matches
the test implementation.
| - accuracy/test_llm_api_autodeploy.py::TestNemotronH::test_auto_dtype[True] | ||
| - accuracy/test_llm_api_autodeploy.py::TestNemotronMOE::test_fp8 | ||
| - accuracy/test_llm_api_autodeploy.py::TestNemotronMOE::test_bf16 | ||
| - accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_bf16 |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# First, find the test file mentioned in the review
echo "=== Finding test file ==="
find . -name "test_llm_api_autodeploy.py" -type f 2>/dev/null | head -5
# Check if the file exists and get basic info
echo ""
echo "=== Checking YAML file ==="
if [ -f "tests/integration/test_lists/test-db/l0_h100.yml" ]; then
echo "YAML file found. Getting context around line 120:"
sed -n '100,130p' tests/integration/test_lists/test-db/l0_h100.yml | cat -n
fiRepository: NVIDIA/TensorRT-LLM
Length of output: 2660
🏁 Script executed:
#!/bin/bash
# Search for skip_less_device definition and test_bf16 in test files
echo "=== Looking for skip_less_device definition ==="
rg "skip_less_device" . --type py 2>/dev/null | head -20
echo ""
echo "=== Searching for test_bf16 in test_llm_api_autodeploy.py ==="
rg -A 10 "def test_bf16" tests/integration/defs/accuracy/test_llm_api_autodeploy.py 2>/dev/null | head -30Repository: NVIDIA/TensorRT-LLM
Length of output: 2852
🏁 Script executed:
#!/bin/bash
echo "=== Finding TestNemotronSuperV3 class definition ==="
rg -B 5 "class TestNemotronSuperV3" tests/integration/defs/accuracy/test_llm_api_autodeploy.py
echo ""
echo "=== Finding all test_bf16 occurrences with context ==="
rg -B 3 "def test_bf16" tests/integration/defs/accuracy/test_llm_api_autodeploy.py
echo ""
echo "=== Checking for skip_less_device definition ==="
rg -B 2 -A 5 "skip_less_device" tests/integration/conftest.py 2>/dev/null | head -40Repository: NVIDIA/TensorRT-LLM
Length of output: 709
🏁 Script executed:
#!/bin/bash
# Search for skip_less_device in conftest files throughout the project
echo "=== Finding skip_less_device definition ==="
find . -name "conftest.py" -type f -exec grep -l "skip_less_device" {} \; 2>/dev/null
# Show the definition
for f in $(find . -name "conftest.py" -type f -exec grep -l "skip_less_device" {} \; 2>/dev/null); do
echo "=== Found in: $f ==="
rg -B 2 -A 10 "def.*skip_less_device" "$f"
doneRepository: NVIDIA/TensorRT-LLM
Length of output: 318
🏁 Script executed:
#!/bin/bash
echo "=== Checking conftest.py for skip_less_device definition ==="
rg "skip_less_device" tests/integration/defs/conftest.py -B 5 -A 10
echo ""
echo "=== Also check if it's imported or defined elsewhere ==="
rg -A 5 "pytest.mark.skip_less_device" tests/integration/defs/conftest.pyRepository: NVIDIA/TensorRT-LLM
Length of output: 1384
🏁 Script executed:
#!/bin/bash
# Get more complete view of TestNemotronSuperV3 and its test_bf16
echo "=== Complete TestNemotronSuperV3 class and test_bf16 ==="
rg -A 30 "class TestNemotronSuperV3" tests/integration/defs/accuracy/test_llm_api_autodeploy.py
echo ""
echo "=== Check TestNemotronMOE test_bf16 for comparison ==="
rg -B 10 "class TestNemotronMOE" tests/integration/defs/accuracy/test_llm_api_autodeploy.py | tail -20Repository: NVIDIA/TensorRT-LLM
Length of output: 1757
🏁 Script executed:
#!/bin/bash
echo "=== Get complete test_bf16 method for TestNemotronSuperV3 ==="
sed -n '1,500p' tests/integration/defs/accuracy/test_llm_api_autodeploy.py | tail -200 | rg -A 20 "class TestNemotronSuperV3" | head -50Repository: NVIDIA/TensorRT-LLM
Length of output: 972
🏁 Script executed:
#!/bin/bash
echo "=== Find the exact line numbers and full test_bf16 implementation ==="
grep -n "class TestNemotronSuperV3" tests/integration/defs/accuracy/test_llm_api_autodeploy.py
echo ""
echo "=== Extract from that class to find test_bf16 ==="
START_LINE=$(grep -n "class TestNemotronSuperV3" tests/integration/defs/accuracy/test_llm_api_autodeploy.py | cut -d: -f1)
echo "Class starts at line: $START_LINE"
# Show next 150 lines from class definition
sed -n "${START_LINE},$((START_LINE+150))p" tests/integration/defs/accuracy/test_llm_api_autodeploy.py | cat -nRepository: NVIDIA/TensorRT-LLM
Length of output: 2362
Move this test to a condition block requiring 8 GPUs.
The test is decorated with @pytest.mark.skip_less_device(8) (lines 32-34), indicating it requires 8 GPUs, but is placed in a condition block with system_gpu_count: gte: 1, lte: 1. The skip_less_device fixture will skip the test when the device count is less than the required count, so this test will never execute under the current condition.
Either move to a system_gpu_count: gte: 8 condition block or remove the decorator if fewer GPUs are sufficient.
🤖 Prompt for AI Agents
In tests/integration/test_lists/test-db/l0_h100.yml around line 120, the listed
test accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_bf16 is
inside a condition block limited to system_gpu_count: gte: 1, lte: 1 while the
test is decorated with @pytest.mark.skip_less_device(8); move this test entry
into a condition block that requires system_gpu_count: gte: 8 (or create a new
block with gte: 8) so it can actually run on 8+ GPU systems, or alternately
remove the @pytest.mark.skip_less_device(8) decorator in the test if it truly
only needs 1 GPU.
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
- Fix MLP dims to support latent dimension - Rename embedding -> embeddings in state dict Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
galagam
force-pushed
the
chenghao/super-v3-acc-1219
branch
from
67fd573 to
0f99b6e
Compare
Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
2 participants
Summary by CodeRabbit
Tests
Chores
✏️ Tip: You can customize this high-level summary in your review settings.
Description
Test Coverage
accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_bf16
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.