Skip to content

Conversation

QiJune
Copy link
Collaborator

@QiJune QiJune commented Jul 23, 2025

Summary by CodeRabbit

  • Refactor
    • Removed unused attributes and simplified internal logic for request handling, resulting in a cleaner and more maintainable codebase. No changes to user-facing features or behavior.

@QiJune QiJune requested a review from a team as a code owner July 23, 2025 06:34
@QiJune QiJune requested a review from Naveassaf July 23, 2025 06:34
Copy link
Contributor

coderabbitai bot commented Jul 23, 2025

Walkthrough

This change removes the has_context_request attribute and related logic from both the ExecutorRequestQueue and PyExecutor classes. Associated imports and conditional code blocks are deleted, simplifying the initialization and request handling logic without altering overall control flow.

Changes

File(s) Change Summary
tensorrt_llm/_torch/pyexecutor/executor_request_queue.py Removed has_context_request attribute, its initialization, related code blocks, and unused import.
tensorrt_llm/_torch/pyexecutor/py_executor.py Removed self.active and self.has_context_request attributes; simplified dummy request logic accordingly.

Sequence Diagram(s)

No sequence diagram generated, as the changes are limited to attribute and logic removal without altering control flow.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

  • feat: Refactor the fetching request logic #5786: Refactored and introduced the ExecutorRequestQueue class and its integration into PyExecutor, including the initial use of has_context_request, which is now being removed and simplified by this PR.

Suggested reviewers

  • HuiGao-NV
  • pcastonguay

Poem

A rabbit hopped through lines of code,
Removing flags that once bestowed.
No more context checks to keep,
The logic now is clear and neat.
With every hop, the code grew light—
Simpler paths for tasks in flight!
🐇✨

Note

⚡️ Unit Test Generation - Beta

CodeRabbit's unit test generation is now available in Beta! Automatically generate comprehensive unit tests for your code changes, ensuring better test coverage and catching edge cases you might miss. Our AI analyzes your code structure and creates tests that follow best practices and your project's testing patterns. Learn more here, or just try it under ✨ Finishing Touches.

✨ Finishing Touches
  • 📝 Generate Docstrings
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai generate unit tests to generate unit tests for this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@QiJune
Copy link
Collaborator Author

QiJune commented Jul 23, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #12662 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #12662 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #9416 completed with status: 'FAILURE'

@QiJune
Copy link
Collaborator Author

QiJune commented Jul 23, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #12668 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #12668 [ run ] completed with state FAILURE

@QiJune
Copy link
Collaborator Author

QiJune commented Jul 23, 2025

/bot run

@tensorrt-cicd
Copy link
Collaborator

PR_Github #12702 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #12702 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #9450 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

Copy link
Collaborator

@jinyangyuan-nvidia jinyangyuan-nvidia left a comment

Choose a reason for hiding this comment

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

LGTM

Signed-off-by: junq <[email protected]>
@QiJune
Copy link
Collaborator Author

QiJune commented Jul 24, 2025

/bot skip --comment "skip for code comment changes"

Copy link
Contributor

@coderabbitai coderabbitai bot 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/pyexecutor/py_executor.py (1)

1152-1152: Documentation improvement enhances clarity.

The updated docstring accurately reflects that this method specifically pads with generation dummy requests, which aligns with the hardcoded is_gen=True parameter. However, the line exceeds the 120-character limit.

Consider wrapping the docstring to stay within line length limits:

-        Pad with a generation dummy request, if required, to ensure every attention_dp rank has at least one active request.
+        Pad with a generation dummy request, if required, to ensure every 
+        attention_dp rank has at least one active request.
📜 Review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 7f184d3 and a055eff.

📒 Files selected for processing (1)
  • tensorrt_llm/_torch/pyexecutor/py_executor.py (2 hunks)
🧰 Additional context used
🧠 Learnings (1)
tensorrt_llm/_torch/pyexecutor/py_executor.py (1)

Learnt from: yechank-nvidia
PR: #6254
File: tensorrt_llm/_torch/pyexecutor/model_engine.py:1201-1204
Timestamp: 2025-07-22T09:22:14.726Z
Learning: In TensorRT-LLM's multimodal processing pipeline, shared tensor recovery using from_shared_tensor() is only needed during the context phase. Generation requests reuse the already-recovered tensor data and only need to call strip_for_generation() to remove unnecessary multimodal data while preserving the recovered tensors. This avoids redundant tensor recovery operations during generation.

🪛 Ruff (0.12.2)
tensorrt_llm/_torch/pyexecutor/py_executor.py

1152-1152: Line too long (124 > 120)

(E501)

⏰ 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/py_executor.py (1)

1170-1171: LGTM! Simplified logic removes unused variable dependency.

The change from conditional flags based on self.has_context_request to unconditional True values correctly reflects the removal of context request tracking. This simplification aligns with the method's purpose of always creating generation dummy requests for attention DP padding.

@tensorrt-cicd
Copy link
Collaborator

PR_Github #12765 [ skip ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #12765 [ skip ] completed with state SUCCESS
Skipping testing for commit a055eff

@QiJune QiJune merged commit 428e340 into NVIDIA:main Jul 24, 2025
3 checks passed
NVShreyas pushed a commit to NVShreyas/TensorRT-LLM that referenced this pull request Jul 28, 2025
Ransiki pushed a commit to Ransiki/TensorRT-LLM that referenced this pull request Jul 29, 2025
lancelly pushed a commit to lancelly/TensorRT-LLM that referenced this pull request Aug 6, 2025
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.

6 participants