[TRTLLM-5252][feat] Add fp8 support for Mistral Small 3.1 #6731
Conversation
📝 WalkthroughWalkthroughMistral3VLM's sub-model config helper now accepts dynamic overrides via **changes, disables vision sub-model quantization (sets vision_config.quant_config=None), and propagates the top-level pretrained_config.torch_dtype into sub-configs when missing. Tests for MistralSmall24B were parameterized to run unquantized and FP8 variants; FP8 accuracy entries were added to three reference YAMLs and test-selection lists updated. Changes
Sequence Diagram(s)sequenceDiagram
participant TestRunner
participant ModelLoader
participant Mistral3VLM
TestRunner->>ModelLoader: load(model_path)
ModelLoader->>Mistral3VLM: _get_sub_model_config(model_config, name, **changes)
Mistral3VLM-->>ModelLoader: return sub-model config (applies **changes, sets vision.quant_config=None, propagates torch_dtype if missing)
ModelLoader-->>TestRunner: loaded model
TestRunner->>Model: assert llm.args.quant_config.quant_algo == expected_quant_algo
TestRunner->>Model: run evaluations (cnn_dailymail, gsm8k, mmlu)
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the "Integrations" page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. 📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (8)
🚧 Files skipped from review as they are similar to previous changes (7)
🧰 Additional context used🧠 Learnings (2)📚 Learning: 2025-07-28T17:06:08.621ZApplied to files:
📚 Learning: 2025-08-06T13:58:07.506ZApplied to files:
⏰ 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)
🔇 Additional comments (2)
✨ 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: 1
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (5)
tensorrt_llm/_torch/models/modeling_mistral.py(2 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(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:
tensorrt_llm/_torch/models/modeling_mistral.pytests/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:
tensorrt_llm/_torch/models/modeling_mistral.pytests/integration/defs/accuracy/test_llm_api_pytorch.py
🧠 Learnings (5)
📓 Common learnings
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: 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: 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: 2025-08-06T03:47:16.802Z
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/defs/accuracy/references/cnn_dailymail.yamltests/integration/defs/accuracy/references/gsm8k.yamltests/integration/defs/accuracy/references/mmlu.yamltensorrt_llm/_torch/models/modeling_mistral.pytests/integration/defs/accuracy/test_llm_api_pytorch.py
📚 Learning: 2025-08-06T03:47:16.802Z
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/defs/accuracy/references/cnn_dailymail.yamltests/integration/defs/accuracy/references/gsm8k.yamltests/integration/defs/accuracy/references/mmlu.yamltensorrt_llm/_torch/models/modeling_mistral.py
📚 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
📚 Learning: 2025-08-06T13:58:07.506Z
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
🔇 Additional comments (6)
tests/integration/defs/accuracy/references/gsm8k.yaml (1)
150-152: LGTM! FP8 quantization entry correctly added.The FP8 quantization configuration follows the established pattern and maintains the same accuracy as the non-quantized version (89.23), indicating effective FP8 implementation for Mistral Small 3.1.
tests/integration/defs/accuracy/references/cnn_dailymail.yaml (1)
202-204: LGTM! FP8 quantization entry properly configured.The FP8 configuration is correctly formatted with a minimal accuracy drop (29.20 → 29.0), which is expected and acceptable for FP8 quantization.
tests/integration/defs/accuracy/references/mmlu.yaml (1)
108-110: LGTM! Consistent FP8 quantization configuration.The FP8 entry is properly formatted with a reasonable accuracy drop (81.7 → 81.1), maintaining good performance while enabling quantization benefits.
tensorrt_llm/_torch/models/modeling_mistral.py (2)
303-306: LGTM! Proper handling of vision model quantization.The explicit disabling of quantization for the vision model is well-documented and aligns with the current
modeloptlimitations. This ensures the FP8 quantization is applied only to supported components.
402-402: LGTM! Enhanced flexibility for sub-model configuration.The addition of
**changesparameter to_get_sub_model_configenables dynamic configuration overrides, which is essential for selectively applying quantization settings. This is a clean implementation that supports the FP8 quantization requirements.Also applies to: 409-409
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
707-715: LGTM!The test method implementation is well-structured with proper parametrization to test both quantized and non-quantized models. The quantization algorithm assertion ensures correct model loading, and the comprehensive task evaluation provides good test coverage.
2ez4bz
force-pushed
the
dev-mistral3-fp8
branch
from
1be7257 to
3f91b10
Compare
|
/bot run |
|
PR_Github #14916 [ run ] triggered by Bot |
|
PR_Github #14916 [ run ] completed with state |
|
/bot --reuse-pipeline |
GitHub Bot Help
Provide a user friendly way for developers to interact with a Jenkins server. Run See details below for each supported subcommand.
Launch build/test pipelines. All previously running jobs will be killed.
kill
Kill all running builds associated with pull request. skip
Skip testing for latest commit on pull request. reuse-pipeline
Reuse 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. |
|
/bot run |
|
PR_Github #15014 [ run ] triggered by Bot |
|
PR_Github #15014 [ run ] completed with state |
2ez4bz
force-pushed
the
dev-mistral3-fp8
branch
from
3f91b10 to
cbc459f
Compare
|
/bot run |
|
PR_Github #15026 [ run ] triggered by Bot |
|
PR_Github #15026 [ run ] completed with state |
2ez4bz
force-pushed
the
dev-mistral3-fp8
branch
from
cbc459f to
e81302f
Compare
|
/bot run |
|
PR_Github #15071 [ run ] triggered by Bot |
|
PR_Github #15071 [ run ] completed with state |
2ez4bz
force-pushed
the
dev-mistral3-fp8
branch
from
e81302f to
8f84def
Compare
|
/bot run |
|
PR_Github #15191 [ run ] completed with state |
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit adds some level of FP8 support to Mistral Small 3.1 by: * disabling quantization for the vision sub-model since `modelopt` does support quantizing it (yet). * extending existing accuracy tests to use a modelopt produced FP8 checkpoint. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
4 participants
Summary by CodeRabbit
Bug Fixes
New Features
Tests
Chores
[TRTLLM-5252][feat] Add fp8 support for Mistral Small 3.1
Description
This commit adds FP8 support to Mistral Small 3.1, but only for the language model portion.
Test Coverage
Existing accuracy test extended to cover FP8.
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.