[https://nvbugs/5437405][fix] cherry-pick PR 7000 (qwen3 235b eagle3 ci) #7702
Conversation
Signed-off-by: bhsueh <[email protected]>
📝 WalkthroughWalkthroughAdds 4-GPU NVFP4 MoE test cases (including Eagle3/speculative decoding options) in PyTorch accuracy tests, updates an existing NVFP4 parameterization, renames corresponding test identifiers in QA lists, and updates test database YAMLs to include the new test and adjust/remove related entries and timeouts. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests
Tip 👮 Agentic pre-merge checks are now available in preview!Pro plan users can now enable pre-merge checks in their settings to enforce checklists before merging PRs.
Please see the documentation for more information. Example: reviews:
pre_merge_checks:
custom_checks:
- name: "Undocumented Breaking Changes"
mode: "warning"
instructions: |
Pass/fail criteria: All breaking changes to public APIs, CLI flags, environment variables, configuration keys, database schemas, or HTTP/GraphQL endpoints must be documented in the "Breaking Change" section of the PR description and in CHANGELOG.md. Exclude purely internal or private changes (e.g., code not exported from package entry points or explicitly marked as internal).Please share your feedback with us on this Discord post. 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. Comment |
|
/bot run |
|
PR_Github #18544 [ run ] triggered by Bot |
![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 (3)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (2)
2296-2304: Add rationale for toggling KV cache reuse wheneagle3=Trueand keep comments consistent.You added the
eagle3parameter and (below in the body) flipenable_block_reuse=not eagle3. Elsewhere (e.g., Llama3.1 EAGLE3 tests) we explicitly allow reuse. Please add a short note or NVBugs ref clarifying why Qwen3-235B needs reuse disabled under EAGLE3, or align behavior if not required. Also, the new ID “latency_moe_trtllm_eagle3” looks good and matches the lists.
2343-2385: Strengthen the new 4‑GPU NVFP4 test with invariants and clarify the TP8 note.
- Please assert the expected backend and quant algo (mirrors DeepSeek‑R1 tests) to catch mis‑loads early.
- The inline comment says “TP8 has bug…” while this case runs on TP4. Reword to explain why we run TP4 with EAGLE3 + TRTLLM and, if possible, reference the NVBug you’re fixing.
Apply this diff inside
test_nvfp4_4gpus:@@ - [ - (4, 1, 4, False, False, False, "TRTLLM", - True), # TP8 has bug when we use TRTLLM moe backend and eagle3 - ], + [ + # TRTLLM MoE + EAGLE3 is unstable at TP8; use TP4 for CI. See nvbugs/5437405. + (4, 1, 4, False, False, False, "TRTLLM", True), + ], @@ - with LLM( + with LLM( f"{llm_models_root()}/Qwen3/saved_models_Qwen3-235B-A22B_nvfp4_hf", tensor_parallel_size=tp_size, pipeline_parallel_size=pp_size, moe_expert_parallel_size=ep_size, **pytorch_config, enable_attention_dp=attention_dp, kv_cache_config=kv_cache_config, speculative_config=spec_config) as llm: + # Sanity invariants to fail fast if a wrong artifact is picked up. + assert llm.args.moe_config.backend == moe_backend + assert llm.args.quant_config.quant_algo == QuantAlgo.NVFP4tests/integration/test_lists/test-db/l0_gb200.yml (1)
69-69: Additive entry looks correct; consider pre‑merge coverage if intended.The new test path and ID match the function. If you want this to run pre‑merge too, add it to the pre‑merge block above; otherwise this post‑merge‑only addition is fine.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (5)
tests/integration/defs/accuracy/test_llm_api_pytorch.py(2 hunks)tests/integration/test_lists/qa/llm_function_full.txt(1 hunks)tests/integration/test_lists/qa/llm_function_sanity.txt(1 hunks)tests/integration/test_lists/test-db/l0_gb200.yml(1 hunks)tests/integration/test_lists/test-db/l0_gb200_multi_nodes.yml(1 hunks)
🧰 Additional context used
📓 Path-based instructions (3)
**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Use only spaces, no tabs; indent with 4 spaces.
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
🧠 Learnings (4)
📓 Common learnings
Learnt from: venkywonka
PR: NVIDIA/TensorRT-LLM#6029
File: .github/pull_request_template.md:45-53
Timestamp: 2025-08-27T17:50:13.264Z
Learning: For PR templates in TensorRT-LLM, avoid suggesting changes that would increase developer overhead, such as converting plain bullets to mandatory checkboxes. The team prefers guidance-style bullets that don't require explicit interaction to reduce friction in the PR creation process.
📚 Learning: 2025-08-13T11:07:11.772Z
Learnt from: Funatiq
PR: NVIDIA/TensorRT-LLM#6754
File: tests/integration/test_lists/test-db/l0_a30.yml:41-47
Timestamp: 2025-08-13T11:07:11.772Z
Learning: In TensorRT-LLM test configuration files like tests/integration/test_lists/test-db/l0_a30.yml, TIMEOUT values are specified in minutes, not seconds.
Applied to files:
tests/integration/test_lists/test-db/l0_gb200.ymltests/integration/test_lists/test-db/l0_gb200_multi_nodes.yml
📚 Learning: 2025-09-09T09:40:45.658Z
Learnt from: fredricz-20070104
PR: NVIDIA/TensorRT-LLM#7645
File: tests/integration/test_lists/qa/llm_function_core.txt:648-648
Timestamp: 2025-09-09T09:40:45.658Z
Learning: In TensorRT-LLM test lists, it's common and intentional for the same test to appear in multiple test list files when they serve different purposes (e.g., llm_function_core.txt for comprehensive core functionality testing and llm_function_core_sanity.txt for quick sanity checks). This duplication allows tests to be run in different testing contexts.
Applied to files:
tests/integration/test_lists/test-db/l0_gb200.ymltests/integration/test_lists/qa/llm_function_full.txttests/integration/test_lists/qa/llm_function_sanity.txt
📚 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/test_lists/qa/llm_function_full.txttests/integration/defs/accuracy/test_llm_api_pytorch.py
🧬 Code graph analysis (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (4)
tensorrt_llm/llmapi/llm_args.py (5)
CudaGraphConfig(106-163)MoeConfig(166-187)KvCacheConfig(923-1002)EagleDecodingConfig(406-432)speculative_model_dir(1321-1322)tests/integration/defs/conftest.py (1)
llm_models_root(77-83)tensorrt_llm/llmapi/llm.py (1)
LLM(1111-1127)tests/integration/defs/accuracy/accuracy_core.py (4)
MMLU(269-283)evaluate(146-199)evaluate(678-688)GSM8K(286-299)
⏰ 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 (4)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
2319-2328: Speculative config path and one‑model mode look correct.
EagleDecodingConfig(max_draft_len=2, ..., eagle3_one_model=True)and the model dir underQwen3/qwen3-235B-eagle3/match the expected spec‑dec wiring for EAGLE3.If there’s a two‑model variant in the repo, do you also want a negative test toggling
eagle3_one_model=Falsefor parity?tests/integration/test_lists/test-db/l0_gb200_multi_nodes.yml (1)
19-20: Confirm reduced timeouts won’t cause flakes.Timeouts for
latency_moe_cutlassandlatency_moe_trtllmare now 90 (minutes). Given multi‑node startup variance, please confirm 90m is sufficient on GB200 clusters; otherwise bump slightly to avoid intermittent timeouts.tests/integration/test_lists/qa/llm_function_full.txt (1)
540-541: Renamed test ID aligns with new function name.
test_nvfp4_4gpus[latency_moe_trtllm_eagle3]correctly replaces the old single‑node ID and matches the Python test’s param IDs.tests/integration/test_lists/qa/llm_function_sanity.txt (1)
103-103: Sanity list entry matches the new 4‑GPU test.Good consistency with the full list. No further changes needed.
|
PR_Github #18544 [ run ] completed with state |
|
/bot run |
|
PR_Github #18571 [ run ] triggered by Bot |
|
PR_Github #18571 [ run ] completed with state |
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…ci) (NVIDIA#7702) Signed-off-by: bhsueh <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
3 participants
Summary by CodeRabbit
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
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.