[None][infra] update feature_combination_matrix of disaggregated and Eagle3 #6945
Conversation
📝 WalkthroughWalkthroughDocumentation updates reflect EAGLE-3 Disaggregated Serving support. Tests are parameterized to toggle eagle3_one_model in the disaggregated single-GPU spec-dec test, and test list entries are expanded to cover both True/False configurations. Changes
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. ✨ 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
|
leslie-fang25
requested review from
Tabrizian and
QiJune
and removed request for
kaiyux and
Shixiaowei02
…Eagle3 Signed-off-by: leslie-fang25 <[email protected]>
leslie-fang25
force-pushed
the
leslie/update_disaggregated_eagle3
branch
from
6d33e9b to
7b073a9
Compare
|
Hi @Tabrizian, I am working on updating the doc of feature combination matrix. For the combination of |
|
/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 (2)
docs/source/torch/features/feature_combination_matrix.md (1)
12-12: Standardize “NO” casing to “No” for consistencyMost entries use “Yes/No/Untested/WIP”. This row uses “NO” (all caps) under Overlap Scheduler, which is inconsistent.
Apply this diff:
-| EAGLE-3(Two Model Engine) | NO | Yes | Yes | Yes | Yes | No | No | --- | | | | | | | +| EAGLE-3(Two Model Engine) | No | Yes | Yes | Yes | Yes | No | No | --- | | | | | | |tests/integration/defs/disaggregated/test_disaggregated_single_gpu.py (1)
352-355: Optional: add ids to parametrization for clarity/debuggabilityAdding readable ids helps when failures occur across the two eagle3 modes.
Example:
-@pytest.mark.parametrize("eagle3_one_model", [True, False]) +@pytest.mark.parametrize( + "eagle3_one_model", + [True, False], + ids=["eagle3_one_model=True", "eagle3_one_model=False"], +)
📜 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 (3)
docs/source/torch/features/feature_combination_matrix.md(1 hunks)tests/integration/defs/disaggregated/test_disaggregated_single_gpu.py(1 hunks)tests/integration/test_lists/test-db/l0_h100.yml(1 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/disaggregated/test_disaggregated_single_gpu.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/disaggregated/test_disaggregated_single_gpu.py
🧬 Code Graph Analysis (1)
tests/integration/defs/disaggregated/test_disaggregated_single_gpu.py (1)
tensorrt_llm/llmapi/llm_args.py (2)
EagleDecodingConfig(418-444)speculative_model_dir(1347-1348)
⏰ 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)
docs/source/torch/features/feature_combination_matrix.md (1)
11-12: Matrix update aligns with new EAGLE-3 disaggregated supportChanging Disaggregated Serving to “Yes” for both EAGLE-3 One-Model and Two-Model engines looks correct given the new test coverage. No functional concerns here.
tests/integration/test_lists/test-db/l0_h100.yml (2)
88-89: Param expansion matches new test signatureAdding both eagle3_one_model=True/False cases for test_disaggregated_spec_dec_batch_slot_limit looks good. The positional ordering in the bracket string follows the established convention in this file: [eagle3_one_model-generation_overlap-spec_dec_model_path-model].
88-89: No stale references found — 4‑arg signature presentBoth occurrences in the test lists include the new leading eagle3_one_model boolean and no other matches were found under tests/integration/test_lists/**.
- tests/integration/test_lists/test-db/l0_h100.yml:88
- disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_spec_dec_batch_slot_limit[True-False-EAGLE3-LLaMA3.1-Instruct-8B-Llama-3.1-8B-Instruct]
- tests/integration/test_lists/test-db/l0_h100.yml:89
- disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_spec_dec_batch_slot_limit[False-False-EAGLE3-LLaMA3.1-Instruct-8B-Llama-3.1-8B-Instruct]
tests/integration/defs/disaggregated/test_disaggregated_single_gpu.py (2)
352-355: LGTM: test now parametrized over eagle3_one_modelAdding eagle3_one_model to the parametrization and function signature is correct. This cleanly exercises both one-model and two-model EAGLE-3 modes in the disaggregated spec-dec test.
359-361: Passing eagle3_one_model through EagleDecodingConfig is correctThis aligns with EagleDecodingConfig.eagle3_one_model and correctly steers spec_dec_mode to EAGLE3_ONE_MODEL vs EAGLE3.
|
PR_Github #15436 [ run ] triggered by Bot |
|
PR_Github #15436 [ run ] completed with state |
|
Yes, it can work with both one-model and two-model. Thanks for updating this doc. |
|
/bot run |
|
PR_Github #15496 [ run ] triggered by Bot |
|
PR_Github #15496 [ run ] completed with state |
Summary by CodeRabbit
Documentation
Tests
Description
This PR update the feature_combination_matrix of
disaggregatedandeagle3. It also add the test configuration for both eagle3 one model and eagle3 two model.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.