[https://nvbugs/5513192][fix] Add the missing param for kv_cache_tran… #7679

nv-guomingz · 2025-09-10T16:05:49Z

…sceiver cases

Summary by CodeRabbit

New Features
- Enhanced KV cache transceiver to support distributed execution, improving scalability for multi-process environments.
Refactor
- Aligned interfaces to accommodate distributed context across context and generation paths.
Tests
- Expanded unit tests to validate distributed behavior, increasing coverage and reliability in multi-process scenarios.

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.

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 the stage-list parameter 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.md
and the scripts/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.

nv-guomingz · 2025-09-10T16:08:33Z

/bot run

tensorrt-cicd · 2025-09-10T16:13:54Z

PR_Github #18385 [ run ] triggered by Bot

coderabbitai · 2025-09-10T16:19:17Z

📝 Walkthrough

Walkthrough

The test updates introduce MPIDist usage and pass a new dist parameter to create_kv_cache_transceiver for both context and generation paths. The API of create_kv_cache_transceiver is extended to accept dist, affecting call sites accordingly.

Changes

Cohort / File(s)	Change summary
Test updates for distributed transceiver `tests/unittest/others/test_kv_cache_transceiver.py`	Imported `MPIDist` and instantiated `dist = MPIDist(mapping=mapping)`. Updated calls to `create_kv_cache_transceiver` to include `dist` for both ctx and gen transceivers.
API signature change `tensorrt_llm._torch.pyexecutor.kv_cache_transceiver`	Function signature changed from `create_kv_cache_transceiver(mapping, kv_cache_manager, attention_type, cache_transceiver_config)` to `create_kv_cache_transceiver(mapping, dist, kv_cache_manager, attention_type, cache_transceiver_config)`.

Sequence Diagram(s)

sequenceDiagram
  autonumber
  actor Test
  participant MPIDist as MPIDist
  participant Factory as create_kv_cache_transceiver
  participant Ctx as Ctx Transceiver
  participant Gen as Gen Transceiver

  Test->>MPIDist: dist = MPIDist(mapping)
  Note over MPIDist: Construct distributed context

  Test->>Factory: create_kv_cache_transceiver(mapping, dist, kv_cache_manager_ctx, attention_type, cfg)
  Factory-->>Ctx: Build context transceiver (uses mapping + dist)

  Test->>Factory: create_kv_cache_transceiver(mapping, dist, kv_cache_manager_gen, attention_type, cfg)
  Factory-->>Gen: Build generation transceiver (uses mapping + dist)

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Pre-merge checks (1 passed, 2 warnings)

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description Check	⚠️ Warning	The PR description contains only the unmodified template placeholders and an incomplete line of text, without any actual explanation of the issue, solution, relevant tests, or confirmation of checklist items, leaving all required sections empty.	Please replace the template placeholders with a clear Description summarizing the change and why it was made, list specific tests in the Test Coverage section, and confirm each item in the PR Checklist to ensure completeness.
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 title clearly references the NVBugs ID and concisely describes the primary change of adding the missing parameter to the kv_cache_transceiver function, making it easy for reviewers to understand the intent and context without including extraneous details.

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 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.

📜 Recent review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 222e016 and 536635b.

📒 Files selected for processing (1)

tests/unittest/others/test_kv_cache_transceiver.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:

tests/unittest/others/test_kv_cache_transceiver.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/unittest/others/test_kv_cache_transceiver.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/unittest/others/test_kv_cache_transceiver.py

🧬 Code graph analysis (1)

tests/unittest/others/test_kv_cache_transceiver.py (2)

tensorrt_llm/_torch/distributed/communicator.py (1)

MPIDist (98-159)

tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py (1)

create_kv_cache_transceiver (31-64)

⏰ 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)

tests/unittest/others/test_kv_cache_transceiver.py (5)

7-7: LGTM! Import addition is correct.

The import of MPIDist is properly added and follows the coding guidelines for maintaining module namespace.

78-78: LGTM! MPIDist instance creation is appropriate.

The MPIDist instance is correctly initialized with the mapping parameter, which aligns with the constructor signature shown in the relevant code snippets.

79-81: Function signature update correctly implemented.

The call to create_kv_cache_transceiver has been properly updated to include the new dist parameter in the correct position (second parameter after mapping), matching the updated function signature.

83-85: Function signature update correctly implemented.

The call to create_kv_cache_transceiver for the generation transceiver has been properly updated to include the new dist parameter in the correct position, consistent with the context transceiver call above.

78-85: Approve MPIDist for single‐process tests
MPIDist’s constructor doesn’t invoke MPI.Init and relies on mpi4py’s automatic initialization at import time, so no explicit MPI setup is needed in a single‐rank context (mpi4py.github.io). All MPIDist operations (broadcast, allgather, barrier, point-to-point) on a communicator of size 1 complete immediately as no inter-process communication is required (learn.microsoft.com).

✨ Finishing Touches

📝 Generate Docstrings

🧪 Generate unit tests

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

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.}

tensorrt-cicd · 2025-09-11T02:31:57Z

PR_Github #18385 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13790 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

…sceiver cases Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

nv-guomingz · 2025-09-11T10:36:41Z

/bot reuse-pipeline

tensorrt-cicd · 2025-09-11T10:41:55Z

PR_Github #18437 [ reuse-pipeline ] triggered by Bot

tensorrt-cicd · 2025-09-11T11:00:14Z

PR_Github #18437 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #18385 for commit 0f4d34b

NVIDIA#7679) Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

nv-guomingz requested review from EmmaQiaoCh, chzblych and pcastonguay September 10, 2025 16:05

nv-guomingz force-pushed the user/guomingz/fix_nvbug_5513192 branch from 536635b to 0d457d7 Compare September 10, 2025 16:08

pcastonguay approved these changes Sep 10, 2025

View reviewed changes

nv-guomingz force-pushed the user/guomingz/fix_nvbug_5513192 branch from 0d457d7 to 0f8d567 Compare September 11, 2025 10:35

[https://nvbugs/5513192][fix] Add the missing param for kv_cache_tran…

0f4d34b

…sceiver cases Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

nv-guomingz force-pushed the user/guomingz/fix_nvbug_5513192 branch from 0f8d567 to 0f4d34b Compare September 11, 2025 10:36

nv-guomingz enabled auto-merge (squash) September 11, 2025 10:36

nv-guomingz merged commit ef676fc into NVIDIA:main Sep 11, 2025
5 checks passed

Wong4j pushed a commit to Wong4j/TensorRT-LLM that referenced this pull request Sep 20, 2025

[https://nvbugs/5513192][fix] Add the missing param for kv_cache_tran… (

977ebb2

NVIDIA#7679) Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

MrGeva pushed a commit to nv-auto-deploy/TensorRT-LLM that referenced this pull request Sep 21, 2025

[https://nvbugs/5513192][fix] Add the missing param for kv_cache_tran… (

93471dd

NVIDIA#7679) Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

nv-guomingz deleted the user/guomingz/fix_nvbug_5513192 branch September 30, 2025 07:45

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[https://nvbugs/5513192][fix] Add the missing param for kv_cache_tran… #7679

[https://nvbugs/5513192][fix] Add the missing param for kv_cache_tran… #7679

Uh oh!

nv-guomingz commented Sep 10, 2025 •

edited

Loading

Uh oh!

nv-guomingz commented Sep 10, 2025

Uh oh!

tensorrt-cicd commented Sep 10, 2025

Uh oh!

coderabbitai bot commented Sep 10, 2025

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Uh oh!

tensorrt-cicd commented Sep 11, 2025

Uh oh!

nv-guomingz commented Sep 11, 2025

Uh oh!

tensorrt-cicd commented Sep 11, 2025

Uh oh!

tensorrt-cicd commented Sep 11, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

[https://nvbugs/5513192][fix] Add the missing param for kv_cache_tran… #7679

[https://nvbugs/5513192][fix] Add the missing param for kv_cache_tran… #7679

Uh oh!

Conversation

nv-guomingz commented Sep 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Description

Test Coverage

PR Checklist

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

nv-guomingz commented Sep 10, 2025

Uh oh!

tensorrt-cicd commented Sep 10, 2025

Uh oh!

coderabbitai bot commented Sep 10, 2025

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Pre-merge checks (1 passed, 2 warnings)

Uh oh!

tensorrt-cicd commented Sep 11, 2025

Uh oh!

nv-guomingz commented Sep 11, 2025

Uh oh!

tensorrt-cicd commented Sep 11, 2025

Uh oh!

tensorrt-cicd commented Sep 11, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

nv-guomingz commented Sep 10, 2025 •

edited

Loading