[None][infra] Enable accuracy test for mtp and chunked prefill #6314
Conversation
📝 WalkthroughWalkthroughThe changes add and parameterize the Changes
Sequence Diagram(s)sequenceDiagram
participant TestRunner
participant TestDeepSeekV3Lite
participant LLM
TestRunner->>TestDeepSeekV3Lite: test_bfloat16(..., enable_chunked_prefill)
TestDeepSeekV3Lite->>LLM: LLM(..., enable_chunked_prefill)
LLM-->>TestDeepSeekV3Lite: (runs test with/without chunked prefill)
TestDeepSeekV3Lite-->>TestRunner: Test result
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 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. 📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (9)
✅ Files skipped from review due to trivial changes (3)
🚧 Files skipped from review as they are similar to previous changes (6)
⏰ 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 comments)
Other keywords and placeholders
Documentation and Community
|
|
/bot run |
leslie-fang25
requested review from
QiJune
and removed request for
chzblych and
yiqingy0
|
PR_Github #12766 [ run ] triggered by Bot |
|
PR_Github #12766 [ run ] completed with state |
leslie-fang25
force-pushed
the
leslie/add_accuracy_test_mtp_chunk_prefill
branch
from
d604a98 to
c17f0ac
Compare
|
/bot run |
|
PR_Github #12813 [ run ] triggered by Bot |
|
PR_Github #12813 [ run ] completed with state |
|
/bot run |
|
PR_Github #12823 [ run ] triggered by Bot |
|
I think you should also enable tests in |
|
PR_Github #12823 [ run ] completed with state |
Thanks for your suggestion. Copied 3 test configuration (all with |
|
/bot run |
![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 (1)
tests/integration/test_lists/test-db/l0_gb200.yml (1)
23-25: Symmetric coverage gap:mtp_nextn=0withenable_chunked_prefill=TruemissingFor completeness you added both
enable_chunked_prefillstates whenmtp_nextn=2, but onlyFalsewhenmtp_nextn=0.
If chunked prefill is expected to work withmtp_nextn=0, add the missing case to prevent silent regressions.+ - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False-enable_chunked_prefill=True]
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tests/integration/test_lists/test-db/l0_gb200.yml(1 hunks)
⏰ 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/test_lists/test-db/l0_gb200.yml (1)
23-25: Check world-size expectation vs. test identifierThese three new entries don’t carry the
_4gpussuffix that the rest of the suite uses to indicate a 4-GPU world size, yet they run under a matrix whosesystem_gpu_counthard-filters to 4.
If the underlying test fixture implicitly assumesworld_size==1, the jobs will waste three GPUs; if it expects four, the missing suffix can make grepping / reporting inconsistent.Please verify that these variants actually spawn four ranks (or adjust the identifier to
_4gpusfor consistency).
|
PR_Github #12850 [ run ] triggered by Bot |
|
PR_Github #12850 [ run ] completed with state |
leslie-fang25
force-pushed
the
leslie/add_accuracy_test_mtp_chunk_prefill
branch
from
ece128d to
b64732c
Compare
|
/bot run |
|
PR_Github #13918 [ run ] completed with state |
leslie-fang25
force-pushed
the
leslie/add_accuracy_test_mtp_chunk_prefill
branch
from
fd53953 to
cb7a677
Compare
|
/bot reuse-pipeline |
|
PR_Github #13944 [ reuse-pipeline ] triggered by Bot |
|
PR_Github #13944 [ reuse-pipeline ] completed with state |
leslie-fang25
force-pushed
the
leslie/add_accuracy_test_mtp_chunk_prefill
branch
from
cb7a677 to
639b7b8
Compare
|
/bot run |
|
PR_Github #14240 [ run ] triggered by Bot |
|
PR_Github #14240 [ run ] completed with state |
leslie-fang25
force-pushed
the
leslie/add_accuracy_test_mtp_chunk_prefill
branch
from
639b7b8 to
8efeda2
Compare
|
/bot run |
|
PR_Github #15389 [ run ] triggered by Bot |
|
PR_Github #15389 [ run ] completed with state |
leslie-fang25
force-pushed
the
leslie/add_accuracy_test_mtp_chunk_prefill
branch
from
8efeda2 to
1929e82
Compare
|
/bot run |
|
PR_Github #15407 [ run ] triggered by Bot |
|
PR_Github #15407 [ run ] completed with state |
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
leslie-fang25
force-pushed
the
leslie/add_accuracy_test_mtp_chunk_prefill
branch
from
1929e82 to
3d5dc9b
Compare
|
/bot run |
|
PR_Github #15558 [ run ] triggered by Bot |
|
PR_Github #15558 [ run ] completed with state |
|
/bot run |
|
PR_Github #15601 [ run ] triggered by Bot |
|
PR_Github #15601 [ run ] completed with state |
4 participants
Summary by CodeRabbit
Description
This PR add the accuracy test combining
mtpandchunked prefillwithTestDeepSeekV3Liteand also update the feature combination matrix.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.