[TRTLLM-5574][test] Add NIM required VLM models multi-gpu test #6687
Conversation
📝 WalkthroughWalkthroughA new parameterized test function Changes
Sequence Diagram(s)sequenceDiagram
participant Pytest
participant test_ptp_quickstart_multimodal_2gpu
participant System
participant QuickstartScript
participant OutputParser
Pytest->>test_ptp_quickstart_multimodal_2gpu: Trigger test with model_name, model_path
test_ptp_quickstart_multimodal_2gpu->>System: Check device count and memory
alt Sufficient devices and memory
test_ptp_quickstart_multimodal_2gpu->>QuickstartScript: Run quickstart_multimodal.py with --tp_size=2 and model-specific args
QuickstartScript-->>test_ptp_quickstart_multimodal_2gpu: Return output
test_ptp_quickstart_multimodal_2gpu->>OutputParser: Parse output and compute match ratio
OutputParser-->>test_ptp_quickstart_multimodal_2gpu: Return match ratio
test_ptp_quickstart_multimodal_2gpu->>Pytest: Assert match ratio >= threshold
else Insufficient resources
test_ptp_quickstart_multimodal_2gpu-->>Pytest: Skip test
end
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~15 minutes Possibly related PRs
Suggested labels
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 (2)
tests/integration/defs/test_e2e.py(7 hunks)tests/integration/test_lists/qa/llm_function_full.txt(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/test_e2e.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/test_e2e.py
🧠 Learnings (4)
📓 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/test_e2e.pytests/integration/test_lists/qa/llm_function_full.txt
📚 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/test_e2e.pytests/integration/test_lists/qa/llm_function_full.txt
📚 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/defs/test_e2e.pytests/integration/test_lists/qa/llm_function_full.txt
🔇 Additional comments (10)
tests/integration/defs/test_e2e.py (10)
33-36: LGTM - Import addition is correct.The addition of
get_device_countto the import statement follows the existing import pattern and is necessary for the device availability checks added later in the test functions.
2116-2116: LGTM - Tensor parallelism parameterization added correctly.The
tp_sizeparameterization with values[1, 2]and appropriate IDs["tp1", "tp2"]is well-structured and follows pytest conventions. This enables testing both single-GPU and dual-GPU scenarios.
2133-2133: LGTM - Function signature updated correctly.The function signature has been properly updated to include the
tp_sizeparameter, maintaining consistency with the parameterization decorator.
2137-2140: LGTM - Device availability check implemented correctly.The device count validation correctly skips the test when insufficient devices are available for the requested
tp_size. The skip message is clear and informative, helping users understand why the test was skipped.
2257-2257: LGTM - Command line argument added correctly.The
tp_sizeparameter is properly passed to the command line execution viaf"--tp_size={tp_size}", maintaining consistency with the existing argument passing pattern.
2333-2333: LGTM - Consistent argument passing in functionality test.The
tp_sizeargument is also correctly passed in the functionality test section, ensuring consistency across all test invocations within the function.
2342-2342: LGTM - Consistent parameterization pattern.The second test function follows the same parameterization pattern as the first, maintaining consistency across the codebase.
2344-2345: LGTM - Function signature maintained correctly.The function signature has been properly updated to include the
tp_sizeparameter while preserving the original parameter order.
2346-2349: LGTM - Consistent device availability check.The device count validation is implemented identically to the first function, ensuring consistent behavior and error messaging across both test functions.
2422-2422: LGTM - Command line argument integration.The
tp_sizeparameter is correctly integrated into the command line arguments, following the same pattern established in the first test function.
crazydemo
force-pushed
the
add_nim_vlm_case
branch
from
46c3129 to
74f2ec6
Compare
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tests/integration/defs/test_e2e.py (1)
2505-2522: Fix line length violation and improve readability.The output validation logic is sound with appropriate match ratios and keyword checking. However, Line 2510 exceeds the 120-character limit.
Apply this diff to fix the line length issue:
- assert obs_match_ratio >= match_ratio, f"Incorrect output!\nGenerated \"{prompt_output}\"\nExpected keywords \"{prompt_keywords}\"\n Matched keywords: {matches}\n Observed match ratio {obs_match_ratio} below threshold {match_ratio}" + assert obs_match_ratio >= match_ratio, ( + f"Incorrect output!\nGenerated \"{prompt_output}\"\n" + f"Expected keywords \"{prompt_keywords}\"\n" + f"Matched keywords: {matches}\n" + f"Observed match ratio {obs_match_ratio} below threshold {match_ratio}" + )
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
tests/integration/defs/test_e2e.py(1 hunks)tests/integration/test_lists/qa/llm_function_full.txt(1 hunks)
✅ Files skipped from review due to trivial changes (1)
- tests/integration/test_lists/qa/llm_function_full.txt
🧰 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/test_e2e.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/test_e2e.py
🧠 Learnings (4)
📓 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: 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/test_e2e.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/test_e2e.py
📚 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/defs/test_e2e.py
🪛 Ruff (0.12.2)
tests/integration/defs/test_e2e.py
2510-2510: Line too long (240 > 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 (3)
tests/integration/defs/test_e2e.py (3)
2421-2429: LGTM: Well-structured test function with appropriate decorators.The test function properly uses pytest decorators to ensure hardware requirements (2+ GPUs, 80GB+ memory) and is correctly parameterized over the three NIM-required VLM models mentioned in the PR objectives.
2430-2473: LGTM: Well-organized test data setup.The test data structure is clean and well-organized with appropriate paths, prompts, and model-specific expected keywords. The use of
llm_models_root()and structured dictionaries makes the test data maintainable and clear.
2475-2504: LGTM: Proper command construction with model-specific configurations.The command building logic correctly sets
--tp_size=2for multi-GPU testing and properly handles model-specific configurations:
- Gemma3 gets appropriate flashinfer backend settings
- Phi-4 gets LoRA loading and sequence length configurations
The conditional logic is clear and maintainable.
Signed-off-by: Ivy Zhang <[email protected]>
crazydemo
force-pushed
the
add_nim_vlm_case
branch
from
74f2ec6 to
64a3739
Compare
|
/bot run --skip-test |
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tests/integration/defs/test_e2e.py (1)
2507-2521: Fix the long line to comply with coding standards.The accuracy validation logic is sound and follows the existing pattern, but line 2510 exceeds the 120-character limit.
Apply this diff to fix the formatting issue:
- assert obs_match_ratio >= match_ratio, f"Incorrect output!\nGenerated \"{prompt_output}\"\nExpected keywords \"{prompt_keywords}\"\n Matched keywords: {matches}\n Observed match ratio {obs_match_ratio} below threshold {match_ratio}" + assert obs_match_ratio >= match_ratio, ( + f"Incorrect output!\nGenerated \"{prompt_output}\"\n" + f"Expected keywords \"{prompt_keywords}\"\n" + f"Matched keywords: {matches}\n" + f"Observed match ratio {obs_match_ratio} below threshold {match_ratio}" + )
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
tests/integration/defs/test_e2e.py(1 hunks)tests/integration/test_lists/qa/llm_function_full.txt(1 hunks)
✅ Files skipped from review due to trivial changes (1)
- tests/integration/test_lists/qa/llm_function_full.txt
🧰 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/test_e2e.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/test_e2e.py
🧠 Learnings (4)
📓 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: 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/test_e2e.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/test_e2e.py
📚 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/defs/test_e2e.py
🪛 Ruff (0.12.2)
tests/integration/defs/test_e2e.py
2510-2510: Line too long (240 > 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 (4)
tests/integration/defs/test_e2e.py (4)
2421-2429: LGTM! Test function structure is well-designed.The test function follows established patterns from existing multimodal tests and includes appropriate pytest markers for multi-GPU requirements. The parametrization covers the three VLM models required by NIM as mentioned in the PR objectives.
2430-2448: LGTM! Test setup follows established conventions.The accuracy inputs definition is consistent with existing multimodal tests and appropriately focuses on image modality for the 2-GPU test scenario.
2450-2473: LGTM! Expected keywords are well-defined for accuracy validation.The expected keywords for each model are specific and relevant to the test prompts, providing a solid foundation for accuracy assertions.
2475-2504: LGTM! Command construction with model-specific configurations is appropriate.The command construction properly includes the
--tp_size=2parameter for multi-GPU testing and implements model-specific configurations that match the patterns used in the existingtest_ptp_quickstart_multimodalfunction.
|
PR_Github #14414 [ run ] triggered by Bot |
|
PR_Github #14414 [ run ] completed with state |
|
/bot run --skip-test |
|
PR_Github #14446 [ run ] triggered by Bot |
|
PR_Github #14446 [ run ] completed with state |
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…A#6687) Signed-off-by: Ivy Zhang <[email protected]> Co-authored-by: Larry <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
4 participants
Three multi-gpu test cases are added:
test_e2e.py::test_ptp_quickstart_multimodal_2gpu[gemma-3-27b-it-gemma/gemma-3-27b-it]
test_e2e.py::test_ptp_quickstart_multimodal_2gpu[mistral-small-3.1-24b-instruct-Mistral-Small-3.1-24B-Instruct-2503]
test_e2e.py::test_ptp_quickstart_multimodal_2gpu[Phi-4-multimodal-instruct-multimodals/Phi-4-multimodal-instruct]
Summary by CodeRabbit
Summary by CodeRabbit
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.
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.