[https://nvbugs/5440241][fix] Fix 70B GSM8K Accuracy drop #6967
Conversation
📝 WalkthroughWalkthroughUpdated GSM8K and MMLU accuracy reference values for meta-llama/Llama-3.3-70B-Instruct and adjusted PyTorch integration tests: model paths, SamplingParams (added Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant Tester as Test runner
participant LLM as LLM instance
participant Evaluator as GPQADiamond
rect rgba(135,206,235,0.12)
Tester->>LLM: init(model_path, max_seq_len?, max_batch_size?, kv_cache_config?)
end
Tester->>Evaluator: evaluate(dataset, extra_evaluator_kwargs={apply_chat_template: true})
Evaluator->>LLM: generate(prompts, sampling_params{max_tokens: N, ...})
alt generation success
LLM-->>Evaluator: outputs
Evaluator-->>Tester: metrics (accuracy)
else generation error
LLM-->>Evaluator: error
Evaluator-->>Tester: failure
end
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 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. ✨ Finishing Touches
🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (2)
468-472: Memory safety WAR parameters are appropriate here.Passing max_seq_len=8192, max_batch_size=32 with KvCacheConfig(free_gpu_memory_fraction=0.5) provides headroom and is a pragmatic fix for the large 70B model warmup/decoding phases.
To document the rationale inline for future maintainers, consider adding a short comment:
- with LLM(model_path, + # WAR: reduce KV cache footprint and cap shapes to avoid illegal memory access on 70B FP8/FP4. + # Keep in sync with accuracy references set with max_tokens=256. + with LLM(model_path, tensor_parallel_size=4, max_seq_len=8192, max_batch_size=32, kv_cache_config=kv_cache_config) as llm:
475-476: Minor refactor: de-duplicate SamplingParams across FP8/NVFP4.Avoid repeating the same SamplingParams in both tests to reduce drift risk.
You could define a class-level constant and reuse it:
# Add inside class TestLlama3_3_70BInstruct SAMPLING_PARAMS_70B = SamplingParams( max_tokens=256, temperature=0.0, add_special_tokens=False, )Then replace the two occurrences:
- sampling_params = SamplingParams( - max_tokens=256, - temperature=0.0, - add_special_tokens=False, - ) + sampling_params = self.SAMPLING_PARAMS_70BAlso applies to: 499-499
📜 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
- Linear integration is disabled
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (3)
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(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/accuracy/test_llm_api_pytorch.py
**/*.{cpp,cxx,cc,cu,h,hpp,hxx,hh,cuh,py}
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header (current year) to all source files
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
🧠 Learnings (1)
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Applied to files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
🔇 Additional comments (4)
tests/integration/defs/accuracy/references/mmlu.yaml (1)
66-66: MMLU reference updates for Llama-3.3-70B-Instruct look consistent.The three adjusted accuracies under meta-llama/Llama-3.3-70B-Instruct reflect the new evaluation settings. No schema or formatting issues spotted.
Also applies to: 69-69, 71-71
tests/integration/defs/accuracy/references/gsm8k.yaml (1)
16-16: GSM8K reference updates align with the decoding changes.
- NVFP4+FP8-KV decreased (expected due to quant/limits), FP8(+FP8-KV and plain FP8) increased, which matches the intent of bounding generations with max_tokens=256.
- YAML structure remains valid.
Also applies to: 19-19, 21-21
tests/integration/defs/accuracy/test_llm_api_pytorch.py (2)
466-476: Anchoring decode length and updating model path for 3.3-70B FP8 is the right fix.
- Switching to llama-3.3-models path and adding SamplingParams(max_tokens=256, temperature=0.0, add_special_tokens=False) directly addresses the GSM8K regression from long generations.
- No API issues; this matches the current LLM and SamplingParams signatures.
490-499: NVFP4 test changes (model path, KV cache fraction, LLM caps, max_tokens) are spot on.
- Using the -FP4 variant and asserting QuantAlgo.NVFP4 is correct.
- free_gpu_memory_fraction=0.5 + max_seq_len=8192 + max_batch_size=32 mitigate the illegal memory access you observed.
- Adding max_tokens=256 for SamplingParams aligns this test with the references you updated.
|
/bot run |
|
PR_Github #15535 [ run ] triggered by Bot |
|
PR_Github #15535 [ run ] completed with state |
chenfeiz0326
force-pushed
the
user/chenfeiz/fix-70b-acc-drop
branch
from
87b991b to
bb15eb9
Compare
|
/bot run |
|
PR_Github #15611 [ 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
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled
- Linear integration is disabled
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (3)
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(3 hunks)
🚧 Files skipped from review as they are similar to previous changes (2)
- tests/integration/defs/accuracy/references/mmlu.yaml
- tests/integration/defs/accuracy/references/gsm8k.yaml
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+
Python indentation: 4 spaces, no tabs
Maintain module namespace in imports (from package.subpackage import foo; then use foo.SomeClass())
Python file names use snake_case
Python class names use PascalCase
Python functions/methods and local variables use snake_case; variables starting with a number get k_ prefix (e.g., k_99th_percentile)
Global variables use G_ prefixed UPPER_SNAKE_CASE (e.g., G_MY_GLOBAL)
Constants use UPPER_SNAKE_CASE in Python
Avoid shadowing variables from outer scopes in Python
Initialize all externally visible members of a Python class in init
Prefer docstrings for interfaces used outside a file; comments for local code
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes/variables inline with short docstrings
Avoid reflection when simple alternatives exist (e.g., prefer explicit parameters over dict(**locals()))
In try/except, catch the narrowest exceptions possible
For duck-typing with try/except, keep try body minimal and put logic in else
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
**/*.{cpp,cxx,cc,cu,h,hpp,hxx,hh,cuh,py}
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header (current year) to all source files
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
🧠 Learnings (1)
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Applied to files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
🧬 Code Graph Analysis (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (5)
tests/integration/defs/conftest.py (1)
llm_models_root(77-83)tensorrt_llm/llmapi/llm_args.py (3)
KvCacheConfig(929-1024)quant_config(2152-2155)quant_config(2158-2159)tensorrt_llm/llmapi/llm.py (1)
LLM(1079-1095)tensorrt_llm/quantization/mode.py (1)
QuantAlgo(23-46)tensorrt_llm/sampling_params.py (1)
SamplingParams(125-486)
⏰ 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)
466-476: Good fix: explicit model path + KV cache bound + generation cap to recover GSM8K accuracy
- Updating to the Llama-3.3-70B FP8 path, bounding KV cache via free_gpu_memory_fraction=0.5, setting max_seq_len=8192/max_batch_size=32, and capping SamplingParams.max_tokens=256 with temperature=0.0 are all aligned with the stated goals and should stabilize accuracy and memory behavior for FP8 tp4.
- No API misuses spotted: LLM accepts max_seq_len/max_batch_size via kwargs; SamplingParams.max_tokens is supported.
|
PR_Github #15611 [ run ] completed with state |
|
/bot run |
|
PR_Github #15692 [ run ] triggered by Bot |
chenfeiz0326
force-pushed
the
user/chenfeiz/fix-70b-acc-drop
branch
from
a9d8c0a to
a40a399
Compare
|
/bot run |
|
PR_Github #15722 [ run ] triggered by Bot |
|
PR_Github #15692 [ run ] completed with state |
chenfeiz0326
force-pushed
the
user/chenfeiz/fix-70b-acc-drop
branch
from
a40a399 to
86065fd
Compare
|
/bot run |
|
PR_Github #15764 [ run ] triggered by Bot |
|
PR_Github #15722 [ run ] completed with state |
|
PR_Github #15764 [ run ] completed with state |
chenfeiz0326
force-pushed
the
user/chenfeiz/fix-70b-acc-drop
branch
from
86065fd to
278e8e8
Compare
|
/bot run |
|
PR_Github #15838 [ run ] triggered by Bot |
|
PR_Github #15838 [ run ] completed with state |
Signed-off-by: Chenfei Zhang <[email protected]>
Signed-off-by: Chenfei Zhang <[email protected]>
Signed-off-by: Chenfei Zhang <[email protected]>
chenfeiz0326
force-pushed
the
user/chenfeiz/fix-70b-acc-drop
branch
from
278e8e8 to
3126650
Compare
There was a problem hiding this comment.
Actionable comments posted: 0
♻️ Duplicate comments (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
526-535: 70B NVFP4 tp4 is missing max_seq_len=8192 (can cause illegal memory access per PR objective)The FP8 tp4 block sets max_seq_len=8192, but the NVFP4 tp4 block omits it. The PR’s stated fix for 70B FP4 includes max_seq_len=8192 along with free_gpu_memory_fraction=0.5 and max_batch_size=32. Add max_seq_len to the NVFP4 ctor to avoid illegal memory access and keep configs consistent.
with LLM(model_path, tensor_parallel_size=4, + max_seq_len=8192, max_batch_size=32, kv_cache_config=kv_cache_config) as llm:#!/bin/bash # Verify all 70B Llama-3.3 NVFP4 LLM ctor sites include max_seq_len rg -nP -C2 '(Llama-3\.3-70B-Instruct-FP4)' tests/integration/defs/accuracy/test_llm_api_pytorch.py # Also confirm FP8 tp4 already specifies max_seq_len=8192 rg -nP -C2 '(Llama-3\.3-70B-Instruct-FP8)' tests/integration/defs/accuracy/test_llm_api_pytorch.py | rg -n 'max_seq_len\s*=\s*8192' -n -C2
🧹 Nitpick comments (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
502-509: Optional: clarify why FP8 also uses free_gpu_memory_fraction=0.5PR objective mentions 0.5 specifically for NVFP4 to avoid illegal memory access. If FP8 does not require it, consider removing it (default is 0.9) to reduce cache pressure and improve throughput; otherwise, add a short comment noting why 0.5 is desirable for FP8 here.
- kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.5) + kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.5) # Keep at 0.5 for FP8 to mirror NVFP4 CI headroom
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled
- Linear integration is disabled
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (3)
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(3 hunks)
🚧 Files skipped from review as they are similar to previous changes (2)
- 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 must target Python 3.8+
Python indentation: 4 spaces, no tabs
Maintain module namespace in imports (from package.subpackage import foo; then use foo.SomeClass())
Python file names use snake_case
Python class names use PascalCase
Python functions/methods and local variables use snake_case; variables starting with a number get k_ prefix (e.g., k_99th_percentile)
Global variables use G_ prefixed UPPER_SNAKE_CASE (e.g., G_MY_GLOBAL)
Constants use UPPER_SNAKE_CASE in Python
Avoid shadowing variables from outer scopes in Python
Initialize all externally visible members of a Python class in init
Prefer docstrings for interfaces used outside a file; comments for local code
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes/variables inline with short docstrings
Avoid reflection when simple alternatives exist (e.g., prefer explicit parameters over dict(**locals()))
In try/except, catch the narrowest exceptions possible
For duck-typing with try/except, keep try body minimal and put logic in else
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
**/*.{cpp,cxx,cc,cu,h,hpp,hxx,hh,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header (current year) to all source files
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
🧠 Learnings (2)
📚 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: 2025-08-20T06:56:02.889Z
Learnt from: eopXD
PR: NVIDIA/TensorRT-LLM#6768
File: cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp:577-579
Timestamp: 2025-08-20T06:56:02.889Z
Learning: In cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp, maxSequenceLength is now enforced as a non-optional argument in the BlockManager constructor, so concerns about std::nullopt defaulting to 0 are not applicable. When windowSize > maxSequenceLength, a warning should be added instead of handling optional parameter cases.
Applied to files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
🧬 Code graph analysis (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (5)
tests/integration/defs/conftest.py (1)
llm_models_root(77-83)tensorrt_llm/llmapi/llm_args.py (1)
KvCacheConfig(944-1039)tensorrt_llm/llmapi/llm.py (1)
LLM(1090-1106)tensorrt_llm/quantization/mode.py (1)
QuantAlgo(23-46)tensorrt_llm/sampling_params.py (1)
SamplingParams(125-486)
⏰ 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)
502-512: 70B FP8 tp4: Max tokens bound and harness settings look correctSetting SamplingParams(max_tokens=256) with temperature=0.0 and disabling special tokens aligns with the PR objective to stabilize GSM8K accuracy. The LLM ctor uses tensor_parallel_size=4, max_seq_len=8192, max_batch_size=32, and a conservative KV cache allocation — good balance for CI stability. GPQA uses apply_chat_template via extra_evaluator_kwargs — consistent with other tests.
|
/bot run |
|
PR_Github #16408 [ run ] triggered by Bot |
|
PR_Github #16408 [ run ] completed with state |
Description
This PR fixes Llama3.3 70B fp8/fp4 gsm8k's accuracy drop by adding
max_tokens=256.This PR fixes Llama3.3 70B fp4's illegal memory access by adding
free_gpu_mem_fraction=0.5, max_batch_size=32.FP8 MMLU on H200:
MMLU weighted average accuracy: 80.51 (4104)
FP8 GSM8K on H200:
FP8 GPQA_Diamond on H200:
FP8 MMLU on B200:
MMLU weighted average accuracy: 80.48 (4104)
FP8 GSM8K on B200:
FP8 GPQA_Diamond on B200:
FP4 MMLU on B200:
MMLU weighted average accuracy: 78.78 (4104)
FP4 GSM8K on B200:
FP4 GPQA_Diamond on B200:
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
New Features
Tests