[None][chore] Waive E2E GB200 tests for Gemma3 27B #6916
Conversation
📝 WalkthroughWalkthroughAdds skip markers to Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
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 💡 Knowledge Base configuration:
You can enable these sources in your CodeRabbit configuration. 📒 Files selected for processing (3)
💤 Files with no reviewable changes (1)
🚧 Files skipped from review as they are similar to previous changes (2)
⏰ 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)
✨ 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
🧹 Nitpick comments (1)
tests/integration/test_lists/waives.txt (1)
288-290: Append Jira tracking ID for traceability.Add TRTLLM-7237 to the waiver reason so it’s easy to discover and remove once fixed.
-full:GB200/test_e2e.py::test_ptp_quickstart_multimodal[gemma-3-27b-it-gemma/gemma-3-27b-it-image-True] SKIP (https://nvbugs/5451391) -full:GB200/test_e2e.py::test_ptp_quickstart_multimodal_2gpu[gemma-3-27b-it-gemma/gemma-3-27b-it] SKIP (https://nvbugs/5451391) -full:GB200/test_e2e.py::test_ptp_quickstart_multimodal_multiturn[gemma-3-27b-it-gemma/gemma-3-27b-it] SKIP (https://nvbugs/5451391) +full:GB200/test_e2e.py::test_ptp_quickstart_multimodal[gemma-3-27b-it-gemma/gemma-3-27b-it-image-True] SKIP (https://nvbugs/5451391; tracked via TRTLLM-7237) +full:GB200/test_e2e.py::test_ptp_quickstart_multimodal_2gpu[gemma-3-27b-it-gemma/gemma-3-27b-it] SKIP (https://nvbugs/5451391; tracked via TRTLLM-7237) +full:GB200/test_e2e.py::test_ptp_quickstart_multimodal_multiturn[gemma-3-27b-it-gemma/gemma-3-27b-it] SKIP (https://nvbugs/5451391; tracked via TRTLLM-7237)
📜 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/test_lists/waives.txt(1 hunks)
🔇 Additional comments (1)
tests/integration/test_lists/waives.txt (1)
288-290: Waiver scope and rationale look correct; change aligns with PR intent.Entries are GB200-scoped only, target the Gemma-3 27B multimodal quickstart variants, and reference the NV bug. No API/test logic changes introduced.
brb-nv
force-pushed
the
user/brb/waive-gb200-tests
branch
2 times, most recently
from
03b7254 to
5083f8c
Compare
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tests/integration/defs/test_e2e.py (1)
2129-2131: Optional: Add inline reference to NVBug/Jira to ease future un-waiveAdd a short comment pointing to NVBug 5451391 and TRTLLM-7237 near the mark so the waiver’s reason and cleanup trigger are obvious to future maintainers.
- pytest.param("gemma-3-27b-it", - "gemma/gemma-3-27b-it", - marks=(skip_post_blackwell, - pytest.mark.skip_less_device_memory(80000))), + pytest.param("gemma-3-27b-it", + "gemma/gemma-3-27b-it", + marks=(skip_post_blackwell, + pytest.mark.skip_less_device_memory(80000))), # TEMP: waive on GB200 due to missing vision encoder kernels (NVBug 5451391); track removal via TRTLLM-7237
📜 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/test_e2e.py(3 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/test_e2e.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/test_e2e.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/test_e2e.py
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Pre-commit Check
🔇 Additional comments (3)
tests/integration/defs/test_e2e.py (3)
2129-2131: LGTM: Waiver correctly scoped to GB200 (Blackwell) for Gemma3 27BUsing pytest.param with marks=(skip_post_blackwell, pytest.mark.skip_less_device_memory(80000)) precisely targets GB200 while keeping existing memory gating. Matches PR intent without touching logic.
2429-2431: LGTM: 2-GPU multimodal case correctly waived on GB200Param-level skip_post_blackwell is appropriate here; function-level device/memory marks remain intact. No behavioral changes beyond the intended waiver.
2532-2534: LGTM: Multiturn multimodal case correctly waived on GB200The targeted skip for gemma-3-27b-it aligns with the temporary waiver; keeps the rest of the suite unaffected.
|
/bot run |
|
PR_Github #15454 [ run ] triggered by Bot |
brb-nv
force-pushed
the
user/brb/waive-gb200-tests
branch
from
5083f8c to
46c82ab
Compare
|
/bot run |
|
PR_Github #15465 [ run ] triggered by Bot |
|
PR_Github #15454 [ run ] completed with state |
|
PR_Github #15465 [ run ] completed with state |
|
/bot run |
|
PR_Github #15485 [ run ] triggered by Bot |
|
PR_Github #15485 [ run ] completed with state |
brb-nv
force-pushed
the
user/brb/waive-gb200-tests
branch
from
46c82ab to
c8c294a
Compare
|
/bot run --extra-stage "H100_PCIe-PyTorch-Post-Merge-1" |
There was a problem hiding this comment.
Actionable comments posted: 3
📜 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 (2)
tests/integration/defs/accuracy/test_llm_api_pytorch.py(1 hunks)tests/integration/defs/test_e2e.py(6 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.pytests/integration/defs/test_e2e.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.pytests/integration/defs/test_e2e.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/test_e2e.py
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Pre-commit Check
🔇 Additional comments (5)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (2)
760-761: LGTM: memory-aware KV cache config for Gemma3Using free_gpu_memory_fraction=0.5 together with reuse disabled is a sensible WAR given current kernel gaps for Gemma3. No issues.
767-769: LGTM: explicit CUDA graph opt-out and capacity limitsExplicitly disabling CUDA graphs and bounding max_batch_size/max_seq_len for Gemma3 is aligned with the multimodal path constraints (custom image masks via FLASHINFER). Looks good.
tests/integration/defs/test_e2e.py (3)
2372-2374: LGTM: Gemma3-specific CLI WARs (kv_cache_fraction, max_seq_len)Injecting kv_cache_fraction=0.5 and max_seq_len=1024 for Gemma3 in the quickstart multimodal path is consistent with the FLASHINFER/custom-mask constraints and helps avoid OOM. Good change.
2609-2611: LGTM: Gemma3-specific CLI WARs for 2-GPU pathSame rationale as single-GPU: kv_cache_fraction=0.5 and max_seq_len=1024 are appropriate for Gemma3 with FLASHINFER in 2-GPU runs.
2709-2710: LGTM: Gemma3 multiturn WARs mirroredConsistent use of kv_cache_fraction=0.5 and max_seq_len=1024 for the multiturn multimodal scenario. Good.
|
PR_Github #15493 [ run ] triggered by Bot |
|
PR_Github #15493 [ run ] completed with state |
|
/bot run --extra-stage "H100_PCIe-PyTorch-Post-Merge-1" |
|
PR_Github #15499 [ run ] triggered by Bot |
|
PR_Github #15499 [ run ] completed with state |
brb-nv
force-pushed
the
user/brb/waive-gb200-tests
branch
from
c8c294a to
7e5471a
Compare
|
/bot run --extra-stage "H100_PCIe-PyTorch-Post-Merge-1" |
There was a problem hiding this comment.
Actionable comments posted: 0
♻️ Duplicate comments (3)
tests/integration/defs/test_e2e.py (3)
2235-2236: GB200 waiver won’t trigger with skip_post_blackwell; use a GB200-specific skip markThis won’t skip on GB200 (Blackwell). Replace with the GB200-targeted mark to actually waive these tests per PR intent.
Apply this diff:
- marks=(skip_post_blackwell, + marks=(skip_device_contain_gb200, pytest.mark.skip_less_device_memory(80000))),Add the import (outside this hunk) so the mark resolves:
# in: from .conftest import (...) from .conftest import (..., skip_device_contain_gb200, ...)Run this to confirm the mark exists and is registered in conftest:
#!/bin/bash # Locate conftest and verify the GB200-specific mark fd -t f conftest.py | xargs -I{} rg -n -C3 'skip_device_contain_gb200|skip_device_contain\s*\(\s*\["GB200"\s*\]' {}
2536-2537: Same issue: this won’t skip on GB200Replace skip_post_blackwell with the GB200-specific mark so GB200 is actually waived.
Apply this diff:
- pytest.param( - "gemma-3-27b-it", "gemma/gemma-3-27b-it", marks=skip_post_blackwell), + pytest.param( + "gemma-3-27b-it", "gemma/gemma-3-27b-it", marks=skip_device_contain_gb200),If skip_device_contain_gb200 is not available, fallback to the generic mark if present:
- marks=skip_post_blackwell + marks=pytest.mark.skip_device_contain(["GB200"])
2642-2643: Same issue: GB200 still not waived hereReplace skip_post_blackwell with a GB200-targeted skip.
Apply this diff:
- pytest.param( - "gemma-3-27b-it", "gemma/gemma-3-27b-it", marks=skip_post_blackwell), + pytest.param( + "gemma-3-27b-it", "gemma/gemma-3-27b-it", marks=skip_device_contain_gb200),
🧹 Nitpick comments (3)
tests/integration/defs/test_e2e.py (3)
2372-2373: Use shared constant for kv_cache_fraction for consistencyLeverage the existing _MEM_FRACTION_50 constant instead of hardcoding 0.5.
Apply this diff:
- cmd.append("--kv_cache_fraction=0.5") + cmd.append(f"--kv_cache_fraction={_MEM_FRACTION_50}")
2610-2611: Minor consistency: reuse _MEM_FRACTION_50 instead of literal 0.5Keeps memory tuning centralized.
Apply this diff:
- cmd.append("--kv_cache_fraction=0.5") + cmd.append(f"--kv_cache_fraction={_MEM_FRACTION_50}")
2709-2710: Minor consistency: reuse _MEM_FRACTION_50 instead of literal 0.5Same rationale as above; aligns with other tests in this file.
Apply this diff:
- cmd.append("--kv_cache_fraction=0.5") + cmd.append(f"--kv_cache_fraction={_MEM_FRACTION_50}")
📜 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 (2)
tests/integration/defs/accuracy/test_llm_api_pytorch.py(1 hunks)tests/integration/defs/test_e2e.py(6 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- tests/integration/defs/accuracy/test_llm_api_pytorch.py
🧰 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/test_e2e.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/test_e2e.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/test_e2e.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
|
PR_Github #15545 [ run ] triggered by Bot |
|
PR_Github #15636 [ run ] triggered by Bot |
|
PR_Github #15636 [ run ] completed with state |
|
/bot run --extra-stage "H100_PCIe-PyTorch-Post-Merge-1" |
|
PR_Github #15643 [ run ] triggered by Bot |
|
PR_Github #15643 [ run ] completed with state |
brb-nv
force-pushed
the
user/brb/waive-gb200-tests
branch
from
c248fbf to
789a00d
Compare
|
/bot run --extra-stage "H100_PCIe-PyTorch-Post-Merge-1" |
|
PR_Github #15650 [ run ] triggered by Bot |
|
PR_Github #15650 [ run ] completed with state |
Signed-off-by: Balaram Buddharaju <[email protected]>
brb-nv
force-pushed
the
user/brb/waive-gb200-tests
branch
from
789a00d to
f6be337
Compare
|
/bot run --extra-stage "H100_PCIe-PyTorch-Post-Merge-1" |
|
PR_Github #15655 [ run ] triggered by Bot |
|
PR_Github #15655 [ run ] completed with state |
|
/bot run --extra-stage "H100_PCIe-PyTorch-Post-Merge-1" --disable-fail-fast |
|
PR_Github #15666 [ run ] triggered by Bot |
|
/bot run --extra-stage "H100_PCIe-PyTorch-Post-Merge-1" --disable-fail-fast |
|
PR_Github #15710 [ run ] triggered by Bot |
|
PR_Github #15666 [ run ] completed with state |
|
PR_Github #15710 [ 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: Wangshanshan <[email protected]>
Description
Gemma3 27B tests are failing on GB200 due to missing kernel support for the vision encoder.
https://nvbugspro.nvidia.com/bug/5451391
This MR waives these tests. Long-term solution to be tracked with this: https://jirasw.nvidia.com/browse/TRTLLM-7237.
Also, updates a few Gemma3 tests to make them less memory-demanding.
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
Tests
Chores