[None][infra] add eagle3 one model accuracy tests #6264
Conversation
📝 WalkthroughWalkthroughThe changes parameterize the Changes
Sequence Diagram(s)sequenceDiagram
participant TestRunner
participant TestClass
participant DecodingConfig
participant Evaluation
TestRunner->>TestClass: test_eagle3(overlap_scheduler, eagle3_one_model)
TestClass->>DecodingConfig: create with eagle3_one_model
TestClass->>Evaluation: run evaluation with config
Evaluation-->>TestClass: results
TestClass-->>TestRunner: test outcome
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes 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 with no reviewable changes (1)
🚧 Files skipped from review as they are similar to previous changes (8)
⏰ 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. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
|
/bot run --disable-fail-fast |
![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/defs/accuracy/test_disaggregated_serving.py (1)
344-344: Clarify the comment for max_num_tokens.The comment
# BSis unclear - consider using a more descriptive comment to explain why the generation server has a lower token limit (2048) compared to the context server (13393 * 2).- "max_num_tokens": 2048, # BS + "max_num_tokens": 2048, # Lower token limit for generation server
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tests/integration/defs/accuracy/test_disaggregated_serving.py(1 hunks)
🔇 Additional comments (2)
tests/integration/defs/accuracy/test_disaggregated_serving.py (2)
318-367: LGTM! Well-structured Eagle3 one model accuracy test.The test follows the established pattern and correctly configures Eagle3 speculative decoding with the one model variant enabled. The parameterization over
enable_block_reuseprovides good test coverage.
335-335: Verify asymmetric max_num_tokens configuration is intentional.The context server is configured with
max_num_tokens: 13393 * 2while the generation server usesmax_num_tokens: 2048. This asymmetric configuration differs from the existingtest_eagle3method where both servers use the same value.Please confirm this asymmetric configuration is intentional for the Eagle3 one model test scenario.
Also applies to: 344-344
|
PR_Github #12597 [ run ] triggered by Bot |
|
PR_Github #12597 [ run ] completed with state |
jhaotingc
force-pushed
the
add_disagg_eagle3_test
branch
2 times, most recently
from
f3cf05d to
0df32bb
Compare
jhaotingc
changed the title
|
/bot run --disable-fail-fast |
|
PR_Github #12615 [ run ] triggered by Bot |
|
PR_Github #12615 [ run ] completed with state |
jhaotingc
force-pushed
the
add_disagg_eagle3_test
branch
from
aab7d64 to
dea7c69
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #12664 [ run ] triggered by Bot |
|
PR_Github #12664 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #12733 [ run ] triggered by Bot |
jhaotingc
force-pushed
the
add_disagg_eagle3_test
branch
from
1384cea to
5bf95eb
Compare
|
/bot kill |
|
PR_Github #12742 [ kill ] triggered by Bot |
|
PR_Github #12733 [ run ] completed with state |
|
PR_Github #12742 [ kill ] completed with state |
jhaotingc
force-pushed
the
add_disagg_eagle3_test
branch
from
5bf95eb to
5264dcb
Compare
|
/bot run --disable-fail-fast |
|
/bot run --disable-fail-fast |
|
PR_Github #13716 [ run ] triggered by Bot |
|
PR_Github #13716 [ run ] completed with state |
jhaotingc
changed the title
jhaotingc
force-pushed
the
add_disagg_eagle3_test
branch
2 times, most recently
from
09119c0 to
f465363
Compare
|
/bot run |
|
PR_Github #13843 [ run ] triggered by Bot |
jhaotingc
changed the title
|
PR_Github #13843 [ run ] completed with state |
|
(random failure) |
Signed-off-by: Jhao-Ting Chen <[email protected]>
Signed-off-by: Jhao-Ting Chen <[email protected]>
jhaotingc
force-pushed
the
add_disagg_eagle3_test
branch
from
f465363 to
c977d2a
Compare
|
/bot run |
|
PR_Github #13850 [ run ] triggered by Bot |
|
PR_Github #13850 [ run ] completed with state |
Signed-off-by: Jhao-Ting Chen <[email protected]> Signed-off-by: Lanyu Liao <[email protected]>
Signed-off-by: Jhao-Ting Chen <[email protected]>
Summary by CodeRabbit
Tests
eagle3_one_modelandoverlap_scheduleroptions.Documentation
Description
Related PR:
#4940 @crazydemo
#5558 @Tabrizian
#5879 @xq25478
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.