[TRTLLM-6656][chore] Validate FP8 support for Gemma3 #6678
Conversation
📝 WalkthroughWalkthroughThe updates modify the Gemma3VLM model's sub-model configuration logic to handle quantization settings for text and vision components distinctly, preventing weight loading issues. New FP8 quantization accuracy results are added for several models across multiple datasets, and integration tests are expanded to cover FP8 prequantized models, including additional task evaluations. A new test case is added to the PyTorch backend test list for H100 GPU systems. Changes
Sequence Diagram(s)sequenceDiagram
participant Test as Integration Test
participant ModelLoader as Model Loader
participant Model as Gemma3VLM Model
participant Evaluator as Task Evaluator
Test->>ModelLoader: Load prequantized FP8 model (local path)
ModelLoader->>Model: Instantiate with FP8 quant_config, FLASHINFER backend
Test->>Model: Assert quant_algo == FP8
loop For each task (CnnDailymail, GSM8K, MMLU)
Test->>Evaluator: Evaluate task with Model
Evaluator->>Model: Run inference
Model-->>Evaluator: Return results
Evaluator-->>Test: Report accuracy
end
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~15 minutes Suggested reviewers
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. ✨ 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
|
![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
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (5)
tensorrt_llm/_torch/models/modeling_gemma3vl.py(1 hunks)tests/integration/defs/accuracy/references/cnn_dailymail.yaml(1 hunks)tests/integration/defs/accuracy/references/gsm8k.yaml(1 hunks)tests/integration/defs/accuracy/references/mmlu.yaml(1 hunks)tests/integration/defs/accuracy/test_llm_api_pytorch.py(2 hunks)
🧰 Additional context used
🧠 Learnings (3)
📓 Common learnings
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.
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.
📚 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/defs/accuracy/test_llm_api_pytorch.py
📚 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/defs/accuracy/test_llm_api_pytorch.py
🪛 Ruff (0.12.2)
tests/integration/defs/accuracy/test_llm_api_pytorch.py
755-755: Line too long (127 > 120)
(E501)
⏰ 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 (6)
tests/integration/defs/accuracy/references/cnn_dailymail.yaml (1)
8-10: LGTM! Consistent FP8 quantization entry added.The new accuracy entry for
google/gemma-3-27b-itwith FP8 quantization follows the established pattern in the file. The 1.0 point accuracy drop (28.90 → 27.90) is reasonable for FP8 quantization and aligns with typical quantization trade-offs.tests/integration/defs/accuracy/references/gsm8k.yaml (2)
144-146: LGTM! FP8 quantization entry added for 1B model.The FP8 quantization entry for
google/gemma-3-1b-itis properly formatted and the accuracy drop from 25.52 to 23.96 (1.56 points) is within expected range for FP8 quantization.
149-151: LGTM! FP8 quantization entry added for 27B model.The FP8 quantization entry for
google/gemma-3-27b-itfollows the same pattern as other models in the file. The accuracy drop from 91.66 to 90.66 (1.0 point) is reasonable for FP8 quantization.tests/integration/defs/accuracy/references/mmlu.yaml (1)
117-119: LGTM! Completes FP8 quantization coverage for Gemma3-27B.The FP8 quantization entry for
google/gemma-3-27b-iton MMLU benchmark is consistent with entries in other reference files. The 1.0 point accuracy drop (77.80 → 76.80) aligns with the quantization impact seen in other benchmarks.tensorrt_llm/_torch/models/modeling_gemma3vl.py (1)
137-146: LGTM! Well-designed quantization configuration handling.The conditional
quant_configsetting is well-reasoned:
- Text model preserves quantization config for FP8 support
- Vision model gets
Noneto prevent weight loading failures (since ModelOpt doesn't quantize vision components yet)- Appropriate attention backends chosen based on requirements (FlashInfer for custom mask support in text, TRTLLM for vision)
The implementation correctly uses
dataclasses.replaceand the comments clearly explain the rationale.tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
805-806: LGTM!Good addition of GSM8K task evaluation to improve test coverage for the FP8 prequantized Gemma3 1B model. The implementation follows the established pattern used by other task evaluations in this test method.
brb-nv
force-pushed
the
user/brb/gemma3-fp8
branch
3 times, most recently
from
e26c4e2 to
f3ebdb2
Compare
|
/bot run |
|
PR_Github #14340 [ run ] triggered by Bot |
|
PR_Github #14340 [ run ] completed with state |
|
/bot run |
|
PR_Github #14342 [ run ] triggered by Bot |
|
PR_Github #14342 [ run ] completed with state |
brb-nv
force-pushed
the
user/brb/gemma3-fp8
branch
from
f3ebdb2 to
2b1d2d4
Compare
|
/bot run |
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
754-771: Fix line length violation while maintaining good test structure.The test implementation looks good and follows the established patterns for FP8 prequantized testing. However, there's a line length violation that needs to be addressed.
Apply this diff to fix the line length issue:
- def test_fp8_prequantized(self): + def test_fp8_prequantized(self):The method signature line (755) exceeds the 120-character limit. Consider breaking it into multiple lines if needed, though the current implementation with the model path using
llm_models_root()is already following best practices.The test correctly:
- Disables KV cache reuse as a workaround for Gemma3's sliding window limitations
- Uses FP8 KV cache dtype appropriate for FP8 testing
- Uses FLASHINFER backend for Gemma3 VLM support
- Tests comprehensive accuracy across three different tasks
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (6)
tensorrt_llm/_torch/models/modeling_gemma3vl.py(1 hunks)tests/integration/defs/accuracy/references/cnn_dailymail.yaml(1 hunks)tests/integration/defs/accuracy/references/gsm8k.yaml(1 hunks)tests/integration/defs/accuracy/references/mmlu.yaml(1 hunks)tests/integration/defs/accuracy/test_llm_api_pytorch.py(2 hunks)tests/integration/test_lists/test-db/l0_h100.yml(1 hunks)
✅ Files skipped from review due to trivial changes (1)
- tests/integration/defs/accuracy/references/gsm8k.yaml
🚧 Files skipped from review as they are similar to previous changes (4)
- tests/integration/defs/accuracy/references/cnn_dailymail.yaml
- tests/integration/defs/accuracy/references/mmlu.yaml
- tests/integration/test_lists/test-db/l0_h100.yml
- tensorrt_llm/_torch/models/modeling_gemma3vl.py
🧰 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/accuracy/test_llm_api_pytorch.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/accuracy/test_llm_api_pytorch.py
🧠 Learnings (3)
📓 Common learnings
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/defs/accuracy/test_llm_api_pytorch.py
📚 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/defs/accuracy/test_llm_api_pytorch.py
🪛 Ruff (0.12.2)
tests/integration/defs/accuracy/test_llm_api_pytorch.py
755-755: Line too long (127 > 120)
(E501)
⏰ 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_pytorch.py (1)
805-806: Excellent addition for comprehensive FP8 validation.Adding the GSM8K task evaluation enhances the test coverage for the Gemma3 1B FP8 prequantized model, bringing it in line with the 27B model's three-task validation approach. This provides more comprehensive accuracy validation across different types of tasks (summarization, math reasoning, and general knowledge).
|
PR_Github #14343 [ run ] triggered by Bot |
|
PR_Github #14343 [ run ] completed with state |
brb-nv
force-pushed
the
user/brb/gemma3-fp8
branch
from
2b1d2d4 to
aedb4bc
Compare
Signed-off-by: Balaram Buddharaju <[email protected]>
brb-nv
force-pushed
the
user/brb/gemma3-fp8
branch
from
aedb4bc to
3c20926
Compare
|
/bot run |
|
PR_Github #14478 [ run ] triggered by Bot |
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (6)
tensorrt_llm/_torch/models/modeling_gemma3vl.py(1 hunks)tests/integration/defs/accuracy/references/cnn_dailymail.yaml(1 hunks)tests/integration/defs/accuracy/references/gsm8k.yaml(1 hunks)tests/integration/defs/accuracy/references/mmlu.yaml(1 hunks)tests/integration/defs/accuracy/test_llm_api_pytorch.py(2 hunks)tests/integration/test_lists/test-db/l0_h100.yml(1 hunks)
🚧 Files skipped from review as they are similar to previous changes (5)
- tests/integration/defs/accuracy/references/cnn_dailymail.yaml
- tests/integration/test_lists/test-db/l0_h100.yml
- tensorrt_llm/_torch/models/modeling_gemma3vl.py
- tests/integration/defs/accuracy/references/gsm8k.yaml
- tests/integration/defs/accuracy/references/mmlu.yaml
🧰 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/accuracy/test_llm_api_pytorch.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/accuracy/test_llm_api_pytorch.py
🧠 Learnings (3)
📓 Common learnings
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/defs/accuracy/test_llm_api_pytorch.py
📚 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/defs/accuracy/test_llm_api_pytorch.py
🪛 Ruff (0.12.2)
tests/integration/defs/accuracy/test_llm_api_pytorch.py
755-755: Line too long (127 > 120)
(E501)
⏰ 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 (2)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (2)
806-807: LGTM - Enhanced test coverage.Good addition of GSM8K evaluation to improve mathematical reasoning validation for the FP8 prequantized model. This change is consistent with the pattern used in the new 27B test method and enhances the test coverage appropriately.
754-772: Well-structured FP8 validation test.The new test method follows established patterns and provides comprehensive validation:
- Appropriate KV cache configuration for Gemma3's architecture
- Consistent use of FLASHINFER backend
- Good test coverage with three different evaluation tasks
- Helpful comment about quantization scope (addressing past feedback)
- Proper assertion of quantization algorithm
The test structure is consistent with existing patterns in the codebase and aligns well with the PR objectives.
|
PR_Github #14478 [ run ] completed with state |
Signed-off-by: Balaram Buddharaju <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Balaram Buddharaju <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
4 participants
Description
This MR adds more tests to validate FP8 support for Gemma3 1B and 27B. Also, adds a minor fix to enable weight loading of vision part. The fix wouldn't be needed it ModelOpt quantizes vision part also (which isn't the case today).
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.
Summary by CodeRabbit
Summary by CodeRabbit
Bug Fixes
Tests
Documentation