[https://nvbugs/5448442][fix] Skip trtllm moe backend for sm120 #7010
Conversation
📝 WalkthroughWalkthroughAdds runtime guards to skip NVFP4 tests when the MOE TRTLLM backend runs on GPUs with SM version 120 or 121, removes two Nvfp4 test-list entries, and adds an assert in the fused MoE TRTLLM generator constructor forbidding SM120/121. No public signatures changed. Changes
Sequence Diagram(s)sequenceDiagram
participant Runner as Test Runner
participant Test as NVFP4 Test
participant Env as Backend/SM Detector
Runner->>Test: start test
Test->>Env: get_sm_version(), detect backend
Env-->>Test: SM value, backend type
alt backend == MOE TRTLLM and SM == 120 or 121
Test-->>Runner: skip("MOE TRTLLM backend does not support SM version 120 or 121")
else
Test-->>Runner: proceed with test execution
end
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
✨ 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/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
![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 (5)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (5)
1331-1335: Reduce repetition: cache SM version and use membership testMinor readability/maintainability improvement: call get_sm_version() once and use an in-check instead of two comparisons.
Apply this diff:
- if moe_backend == "TRTLLM" and (get_sm_version() == 120 - or get_sm_version() == 121): - pytest.skip( - "MOE TRTLLM backend does not support SM version 120 or 121") + sm = get_sm_version() + if moe_backend == "TRTLLM" and sm in (120, 121): + pytest.skip("MOE TRTLLM backend does not support SM version 120 or 121")
1383-1387: Same nit: avoid duplicate get_sm_version() callsMirror the same simplification here for consistency.
- if moe_backend == "TRTLLM" and (get_sm_version() == 120 - or get_sm_version() == 121): - pytest.skip( - "MOE TRTLLM backend does not support SM version 120 or 121") + sm = get_sm_version() + if moe_backend == "TRTLLM" and sm in (120, 121): + pytest.skip("MOE TRTLLM backend does not support SM version 120 or 121")
1601-1605: Same nit: collapse condition and cache SM versionKeeps the condition concise and avoids redundant calls.
- if moe_backend == "TRTLLM" and (get_sm_version() == 120 - or get_sm_version() == 121): - pytest.skip( - "MOE TRTLLM backend does not support SM version 120 or 121") + sm = get_sm_version() + if moe_backend == "TRTLLM" and sm in (120, 121): + pytest.skip("MOE TRTLLM backend does not support SM version 120 or 121")
2163-2167: Same nit: usein (120, 121)and a single SM lookupConsistent small cleanup for readability.
- if moe_backend == "TRTLLM" and (get_sm_version() == 120 - or get_sm_version() == 121): - pytest.skip( - "MOE TRTLLM backend does not support SM version 120 or 121") + sm = get_sm_version() + if moe_backend == "TRTLLM" and sm in (120, 121): + pytest.skip("MOE TRTLLM backend does not support SM version 120 or 121")
2288-2292: Same nit: simplify the condition and avoid duplicate callsTiny refactor for clarity.
- if moe_backend == "TRTLLM" and (get_sm_version() == 120 - or get_sm_version() == 121): - pytest.skip( - "MOE TRTLLM backend does not support SM version 120 or 121") + sm = get_sm_version() + if moe_backend == "TRTLLM" and sm in (120, 121): + pytest.skip("MOE TRTLLM backend does not support SM version 120 or 121")
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py(5 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+
Python indentation: 4 spaces, no tabs
Maintain module namespace in imports (from package.subpackage import foo; then use foo.SomeClass())
Python file names use snake_case
Python class names use PascalCase
Python functions/methods and local variables use snake_case; variables starting with a number get k_ prefix (e.g., k_99th_percentile)
Global variables use G_ prefixed UPPER_SNAKE_CASE (e.g., G_MY_GLOBAL)
Constants use UPPER_SNAKE_CASE in Python
Avoid shadowing variables from outer scopes in Python
Initialize all externally visible members of a Python class in init
Prefer docstrings for interfaces used outside a file; comments for local code
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes/variables inline with short docstrings
Avoid reflection when simple alternatives exist (e.g., prefer explicit parameters over dict(**locals()))
In try/except, catch the narrowest exceptions possible
For duck-typing with try/except, keep try body minimal and put logic in else
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
**/*.{cpp,cxx,cc,cu,h,hpp,hxx,hh,cuh,py}
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header (current year) to all source files
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
🧠 Learnings (1)
📚 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/defs/accuracy/test_llm_api_pytorch.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
Signed-off-by: Pamela <[email protected]>
pamelap-nvidia
force-pushed
the
fix_sm120_moe_trtllm
branch
from
7e4022a to
8b4adfa
Compare
|
/bot skip --comment "test only" |
|
PR_Github #15660 [ skip ] triggered by Bot |
|
PR_Github #15660 [ skip ] completed with state |
There was a problem hiding this comment.
@pamelap-nvidia Do we get a clear error message from TRTLLM MoE backend if it is run on these architectures?
As long as that is the case, just skipping the test is fine.
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+
Python indentation: 4 spaces, no tabs
Maintain module namespace in imports (from package.subpackage import foo; then use foo.SomeClass())
Python file names use snake_case
Python class names use PascalCase
Python functions/methods and local variables use snake_case; variables starting with a number get k_ prefix (e.g., k_99th_percentile)
Global variables use G_ prefixed UPPER_SNAKE_CASE (e.g., G_MY_GLOBAL)
Constants use UPPER_SNAKE_CASE in Python
Avoid shadowing variables from outer scopes in Python
Initialize all externally visible members of a Python class in init
Prefer docstrings for interfaces used outside a file; comments for local code
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes/variables inline with short docstrings
Avoid reflection when simple alternatives exist (e.g., prefer explicit parameters over dict(**locals()))
In try/except, catch the narrowest exceptions possible
For duck-typing with try/except, keep try body minimal and put logic in else
Files:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
**/*.{cpp,cxx,cc,cu,h,hpp,hxx,hh,cuh,py}
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header (current year) to all source files
Files:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
🪛 Ruff (0.12.2)
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
71-71: Undefined name get_sm_version
(F821)
Signed-off-by: Pamela <[email protected]>
pamelap-nvidia
force-pushed
the
fix_sm120_moe_trtllm
branch
from
66b9f22 to
0565af1
Compare
|
/bot run |
I added an explicit check in the trtllm MoE module. Previous error message was from lower level checks. |
|
PR_Github #15931 [ run ] triggered by Bot |
|
PR_Github #15931 [ run ] completed with state |
|
/bot run |
|
PR_Github #15934 [ run ] triggered by Bot |
|
PR_Github #15934 [ run ] completed with state |
Signed-off-by: Pamela <[email protected]>
pamelap-nvidia
force-pushed
the
fix_sm120_moe_trtllm
branch
from
21b5d73 to
03d315a
Compare
|
/bot run |
|
PR_Github #15947 [ run ] triggered by Bot |
|
PR_Github #15947 [ run ] completed with state |
Signed-off-by: Pamela <[email protected]>
…IA#7010) Signed-off-by: Pamela <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…IA#7010) Signed-off-by: Pamela <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…IA#7010) Signed-off-by: Pamela <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…IA#7010) Signed-off-by: Pamela <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…IA#7010) Signed-off-by: Pamela <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Summary by CodeRabbit
Description
We don't support SM120 with trtllm MOE backend. Skipping test cases.
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.