Skip to content

Conversation

@achartier
Copy link
Collaborator

@achartier achartier commented Oct 23, 2025

Summary by CodeRabbit

  • Refactor
    • Enhanced internal configuration handling for KV cache retention, improving data propagation through request processing pipeline.

Description

The KV cache retention config of a request are not passed to the C++ request when using the torch backend. This change fixes the behavior.

Test Coverage

Existing torch tests

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 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.

@achartier achartier requested a review from Funatiq October 23, 2025 22:03
@achartier achartier requested a review from a team as a code owner October 23, 2025 22:03
@achartier
Copy link
Collaborator Author

/bot run

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Oct 23, 2025

📝 Walkthrough

Walkthrough

A new kv_cache_retention_config field is passed from executor_request to the LlmRequest constructor in executor_request_to_llm_request. This extends existing request data propagation without modifying public signatures or introducing behavioral changes.

Changes

Cohort / File(s) Summary
KV cache retention config wiring
tensorrt_llm/_torch/pyexecutor/llm_request.py
Added kv_cache_retention_config parameter forwarding from executor request to LlmRequest constructor alongside existing multimodal data wiring

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~5–10 minutes

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)
Check name Status Explanation Resolution
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 (2 passed)
Check name Status Explanation
Title Check ✅ Passed The pull request title "[None][feat] Pass KvCacheRetentionConfig to torch LlmRequest" is specific and clearly describes the main change documented in the raw summary. The title follows the required template format with the ticket identifier and type prefix, accurately reflects that a kv_cache_retention_config field is being passed through to the LlmRequest, and is concise enough for easy scanning of commit history. This directly aligns with the core objective of the PR.
Description Check ✅ Passed The pull request description includes all required sections from the template: the title follows the correct format with "[None][feat]" prefix, a Description section explains the issue and solution clearly, a Test Coverage section is provided specifying "Existing torch tests," and a PR Checklist is completed with the final confirmation checkbox marked. The description adequately conveys what is being changed and why, satisfying the template requirements for a complete submission.
✨ Finishing touches
  • 📝 Generate docstrings
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

📜 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 2392022 and 3cdeb9b.

📒 Files selected for processing (1)
  • tensorrt_llm/_torch/pyexecutor/llm_request.py (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:

  • tensorrt_llm/_torch/pyexecutor/llm_request.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/pyexecutor/llm_request.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/pyexecutor/llm_request.py
⏰ 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/pyexecutor/llm_request.py (1)

767-768: LGTM! Correctly propagates KV cache retention config.

The change properly passes kv_cache_retention_config from the executor request to the LlmRequest constructor, fixing the bug where this configuration was not being propagated to the C++ backend. The implementation follows the established pattern for standard executor request attributes.


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
Copy link
Collaborator

PR_Github #22323 [ run ] triggered by Bot. Commit: 3cdeb9b

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22323 [ run ] completed with state SUCCESS. Commit: 3cdeb9b
/LLM/main/L0_MergeRequest_PR pipeline #16830 completed with status: 'FAILURE'

Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
@Funatiq
Copy link
Collaborator

Funatiq commented Oct 24, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22420 [ run ] triggered by Bot. Commit: e354174

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22420 [ run ] completed with state SUCCESS. Commit: e354174
/LLM/main/L0_MergeRequest_PR pipeline #16897 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

@achartier achartier merged commit cdf0403 into NVIDIA:main Oct 24, 2025
5 checks passed
yufeiwu-nv pushed a commit to yufeiwu-nv/TensorRT-LLM that referenced this pull request Oct 24, 2025
…8634)

Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>
@achartier achartier deleted the llmapi-gds branch October 24, 2025 17:25
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 1, 2025
…8634)

Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025
…8634)

Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025
…8634)

Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Nov 3, 2025
…8634)

Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants