Skip to content

doc: update known issues #6247

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 22, 2025
Merged

doc: update known issues #6247

merged 1 commit into from
Jul 22, 2025

Conversation

QiJune
Copy link
Collaborator

@QiJune QiJune commented Jul 22, 2025

Summary by CodeRabbit

  • Documentation
    • Updated release notes to include a new known issue regarding performance regression with full chunked attention support for LLaMA4 models on sequences longer than 8K tokens.

@QiJune QiJune requested a review from a team as a code owner July 22, 2025 05:38
Copy link
Contributor

coderabbitai bot commented Jul 22, 2025

Walkthrough

The release notes documentation has been updated to mention a new known issue: while full chunked attention support for LLaMA4 models now allows handling sequences longer than 8K tokens, there is a known performance regression. The underlying cause is identified and a fix is planned for a future release.

Changes

File Change Summary
docs/source/release-notes.md Added a new known issue regarding chunked attention support and performance regression for LLaMA4 models.

Estimated code review effort

1 (~2 minutes)

Poem

🐇
In the garden of notes, a new line appears,
Chunked attention for LLaMA4 now cheers!
Sequences stretch, but speed takes a dip—
The cause is in sight, soon fixed on our trip.
Release notes updated, onward we hop,
Awaiting the patch at the next pit stop!
🌱


🪧 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 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.

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)
docs/source/release-notes.md (1)

76-76: Use consistent model naming & tighten wording

Elsewhere in the notes the model is referred to as “Llama 4” or “llama 4”. Using a third variant (LLaMA4) here is jarring. While touching the line, the sentence can read more crisply.

- Full chunked attention support has been added for LLaMA4 to handle >8K sequences, with a known performance regression. The root cause is identified and will be fixed in a future release.
+ While full chunked-attention support for Llama 4 now enables sequences > 8 k tokens, it currently suffers from a known performance regression. The root cause is understood and a fix is planned for a future release.
📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between ab4e178 and 77ee6b0.

📒 Files selected for processing (1)
  • docs/source/release-notes.md (1 hunks)
🧠 Learnings (1)
docs/source/release-notes.md (1)

Learnt from: amitz-nv
PR: #5616
File: tensorrt_llm/executor/worker.py:375-384
Timestamp: 2025-07-17T09:01:27.374Z
Learning: In tensorrt_llm/executor/worker.py, the LoRA adapter cache optimization logic that checks is_adapter_in_cpu_cache() and conditionally passes None for weights/config has a known race condition issue that cannot be solved with simple error handling or verification checks. This is a known limitation that requires a more comprehensive solution.

🧰 Additional context used
🧠 Learnings (1)
docs/source/release-notes.md (1)

Learnt from: amitz-nv
PR: #5616
File: tensorrt_llm/executor/worker.py:375-384
Timestamp: 2025-07-17T09:01:27.374Z
Learning: In tensorrt_llm/executor/worker.py, the LoRA adapter cache optimization logic that checks is_adapter_in_cpu_cache() and conditionally passes None for weights/config has a known race condition issue that cannot be solved with simple error handling or verification checks. This is a known limitation that requires a more comprehensive solution.

@QiJune
Copy link
Collaborator Author

QiJune commented Jul 22, 2025

/bot skip --comment "doc changes"

@QiJune QiJune enabled auto-merge (squash) July 22, 2025 09:14
@tensorrt-cicd
Copy link
Collaborator

PR_Github #12551 [ skip ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #12551 [ skip ] completed with state SUCCESS
Skipping testing for commit 77ee6b0

@QiJune QiJune merged commit 1209001 into NVIDIA:release/0.21 Jul 22, 2025
4 checks passed
@laikhtewari
Copy link
Collaborator

@QiJune @juney-nvidia can we amend the comment to specify which scenarios are affected by the perf issue (ie specifically for seq Len <8k)

@zhuolingwang
Copy link
Collaborator

In 0.21, full chunked attention support has been added to make sure LLaMA4 model can functionally run with > 8K seq length, while there is a known performance regression(only affect LLaMA4 model) due to this functional enhancement. The root cause of the regression has been identified already and the fix will be part of the future release

@laikhtewari Are you OK with above statement or need to add more words?

@QiJune QiJune requested a review from nv-yilinf July 24, 2025 05:20
@QiJune
Copy link
Collaborator Author

QiJune commented Jul 24, 2025

cc @nv-yilinf to comment on the known issue.

This was referenced Jul 24, 2025
dc3671 pushed a commit to dc3671/TensorRT-LLM that referenced this pull request Aug 1, 2025
dc3671 pushed a commit to dc3671/TensorRT-LLM that referenced this pull request Aug 1, 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.

5 participants