Refactor
- Simplified collective reduction setup by using the default strategy, removing hardware-specific conditionals. Streamlines execution paths with no API changes and aims for more consistent behavior across environments.
Chores
- Cleaned up public imports to hide internal strategy configuration details, reducing surface area without affecting user-facing functionality.

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 FollowsTRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (seetest 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.

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: DoesNOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: DoesNOT 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: DoesNOT 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: DoesNOT update GitHub pipeline status.

--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: DoesNOT update GitHub check status.

--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: DoesNOT 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-list parameter to access the appropriate container environment. Note: DoesNOT update GitHub check status.

For guidance on mapping tests to stage names, seedocs/source/reference/ci-overview.md
and thescripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip 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-pipeline

Reuse 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.

Revert "[https://nvbugs/5517023][fix] Pass allreduce strategy and for…

17188ca

…ce NCCL on pre-Blackwell arch (NVIDIA#7768)"This reverts commit88fe78e.Signed-off-by: Tao Li <tali@nvidia.com>

litaotju requested a review froma team as acode owner

September 17, 2025 14:55

Copy link

Contributor

coderabbitaibot commentedSep 17, 2025•
edited
Loading

📝 Walkthrough

Walkthrough

Simplified AllReduce usage in LLaMA model by removing explicit AllReduceStrategy selection and SM-version checks. AllReduce is now instantiated with only the mapping parameter. Also removed AllReduceStrategy from the public import surface. No public APIs changed.

Changes

Cohort / File(s)	Summary of Changes
AllReduce init simplification `tensorrt_llm/_torch/models/modeling_llama.py`	Dropped AllReduceStrategy import and strategy-based branching (e.g., NCCL via get_sm_version). Replaced AllReduce(...) calls to use only the mapping parameter with default strategy. No public signatures changed.

Sequence Diagram(s)

sequenceDiagram  participant Model as LLaMA Model  participant HW as GPU Runtime  participant AR as AllReduce  rect rgb(235, 245, 255)  note over Model,AR: Previous flow  Model->>Model: get_sm_version()  alt SM supports NCCL    Model->>AR: AllReduce(mapping, strategy=NCCL)  else Other    Model->>AR: AllReduce(mapping, strategy=Default)  end  AR->>HW: Execute collective  end  rect rgb(240, 255, 240)  note over Model,AR: New flow  Model->>AR: AllReduce(mapping)  Note: strategy implicit (default)  AR->>HW: Execute collective  end

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Pre-merge checks and finishing touches

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description Check	⚠️ Warning	The PR description contains only the revert commit line and an unfilled copy of the repository template; the Description and Test Coverage sections are empty, the PR checklist items are not completed, and there is no rationale or verification steps explaining why the revert is needed or what behaviors/files are affected (for example the change to tensorrt_llm/_torch/models/modeling_llama.py), so it does not meet the repository's required template completeness.	Please complete the Description with a concise rationale for the revert and a summary of the exact changes being reverted, populate Test Coverage with specific tests or manual verification steps that validate the revert (e.g., tests covering AllReduceStrategy behavior in tensorrt_llm/_torch/models/modeling_llama.py), mark the PR Checklist items as applicable, and assign appropriate reviewers so the change can be properly reviewed and validated.
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	You can run`@coderabbitai generate docstrings` to improve docstring coverage.

✅ Passed checks (1 passed)

Check name	Status	Explanation
Title Check	✅ Passed	The PR title "[https://nvbugs/1234567][fix] Reverthttps://github.com/NVIDIA/TensorRT-LLM/pull/7768/files" explicitly references the NVBugs ticket and the primary action (reverting PR#7768), which matches the PR objective to revert commit`88fe78e` and aligns with the raw_summary's described change; it is concise and directly related to the main change.

✨ Finishing touches

📝 Generate Docstrings

🧪 Generate unit tests

Create PR with unit tests
Post copyable unit tests in a comment

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.

Built-in checks – Quickly apply ready-made checks to enforce title conventions, require pull request descriptions that follow templates, validate linked issues for compliance, and more.
Custom agentic checks – Define your own rules using CodeRabbit’s advanced agentic capabilities to enforce organization-specific policies and workflows. For example, you can instruct CodeRabbit’s agent to verify that API documentation is updated whenever API schema files are modified in a PR. Note: Upto 5 custom checks are currently allowed during the preview period. Pricing for this feature will be announced in a few weeks.

Please see thedocumentation 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 thisDiscord 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.

❤️ Share

_{Comment@coderabbitai help to get the list of available commands and usage tips.}

Copy link

CollaboratorAuthor

litaotju commentedSep 17, 2025

/bot run

Copy link

Collaborator

tensorrt-cicd commentedSep 17, 2025

PR_Github #19018 [ run ] triggered by Bot

coderabbitaibot reviewed

Sep 17, 2025

View reviewed changes

Copy link

Contributor

coderabbitaibot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Actionable comments posted: 0

🧹 Nitpick comments (1)

tensorrt_llm/_torch/models/modeling_llama.py (1)
14-14:Style: keep module namespace for imports (nit).
Per repo guidelines, prefer importing the module then referencing symbols via the module to avoid expanding the public symbol surface of this file.
Example:
fromtensorrt_llm._torchimportdistributedasdist# usage:dist.AllReduce,dist.AllReduceParams,dist.AllReduceFusionOp,dist.MoEAllReduce

📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between22c120e and17188ca.

📒 Files selected for processing (1)

tensorrt_llm/_torch/models/modeling_llama.py (2 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:

tensorrt_llm/_torch/models/modeling_llama.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:

tensorrt_llm/_torch/models/modeling_llama.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:

tensorrt_llm/_torch/models/modeling_llama.py

🧬 Code graph analysis (1)

tensorrt_llm/_torch/models/modeling_llama.py (3)

tensorrt_llm/functional.py (1)
AllReduceParams (3899-3938)
tensorrt_llm/_torch/distributed/ops.py (1)
AllReduce (362-491)
tensorrt_llm/_torch/models/checkpoints/base_weight_mapper.py (1)
mapping (152-153)

⏰ 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)

tensorrt_llm/_torch/models/modeling_llama.py (1)
298-301:Make AllReduce strategy handling consistent (revert intent).
Found explicit strategy usage in tensorrt_llm/_torch/models/modeling_llama.py at lines 298–300 and 449–451; LlamaDecoderLayer at 649 uses mapping-only. Choose one approach and apply uniformly.
Option A (recommended — drop explicit strategy):
@@-        self.all_reduce = AllReduce(-            mapping=model_config.mapping,-            strategy=model_config.allreduce_strategy,-        )+        self.all_reduce = AllReduce(mapping=model_config.mapping)
Apply to Llama4MoE.init (298–301) and Llama4DecoderLayer.init (448–451).
Option B: add strategy at 649 instead if explicit control is required.
Note: repo also contains explicit AllReduce uses in modeling_qwen3_moe.py, modeling_deepseekv3.py, tensorrt_llm/_torch/modules/linear.py, modules/fused_moe/* and tests — consider repo-wide consistency.

juney-nvidia approved these changes

Sep 17, 2025

View reviewed changes

juney-nvidiaenabled auto-merge (squash)

September 17, 2025 15:04

Copy link

Collaborator

tensorrt-cicd commentedSep 17, 2025

PR_Github #19018 [ run ] completed with stateSUCCESS
/LLM/release-1.0/L0_MergeRequest_PR pipeline #415 completed with status: 'SUCCESS'

juney-nvidia merged commit015e149 intoNVIDIA:release/1.0

Sep 17, 2025

5 checks passed

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request

Sep 23, 2025