Skip to content

Conversation

ngxson
Copy link
Owner

@ngxson ngxson commented Jul 24, 2025

This could be useful for hybrid or recurrent models

Summary by CodeRabbit

  • New Features

    • Added support for new model configuration options, including "flash attention" and "SWA full", when loading models.
  • Bug Fixes

    • Improved error handling for cache rollback failures, ensuring cache consistency and more robust model token management.
    • Enhanced token removal logic to correctly reflect success status and handle unsupported scenarios.
  • Chores

    • Updated internal dependencies and WebAssembly binary URLs to version 2.3.4.
    • Incremented package version to 2.3.4.

Copy link

coderabbitai bot commented Jul 24, 2025

Walkthrough

This update introduces new optional configuration fields (swa_full, flash_attn) for model loading in both backend (C++ and TypeScript) and frontend interfaces. It enhances error handling and status reporting in the KV cache removal logic. The update also increments the package version and updates related WebAssembly CDN URLs.

Changes

Files/Groups Change Summary
cpp/actions.hpp Extended action_load to support swa_full and flash_attn; improved error handling and success flag in action_kv_remove.
cpp/glue.hpp, src/glue/messages.ts Added nullable/optional boolean fields flash_attn and swa_full to load request messages.
src/wllama.ts Added optional flash_attn to LoadModelConfig; enhanced error handling in computeNonCachedTokens.
llama.cpp Updated subproject commit reference.
package.json Bumped version from 2.3.3 to 2.3.4.
src/wasm-from-cdn.ts Updated CDN URLs to reference version 2.3.4 of WebAssembly binaries.

Sequence Diagram(s)

sequenceDiagram
    participant Client
    participant TS_Interface as TypeScript Interface
    participant Cpp_Backend as C++ Backend

    Client->>TS_Interface: Send load_req (with flash_attn, swa_full)
    TS_Interface->>Cpp_Backend: Forward load_req (with flash_attn, swa_full)
    Cpp_Backend-->>TS_Interface: Respond load_res
    TS_Interface-->>Client: Return load_res
Loading
sequenceDiagram
    participant App
    participant Wllama
    participant KV_Cache

    App->>Wllama: computeNonCachedTokens(seq)
    Wllama->>KV_Cache: kvRemove(seq)
    alt kvRemove success
        Wllama-->>App: Return uncached suffix of seq
    else kvRemove fails
        Wllama->>KV_Cache: kvClear()
        Wllama-->>App: Return full seq
    end
Loading

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~18 minutes

Possibly related PRs

Poem

🐇
New flags for loading, new checks for cache,
With version bumps, we make a dash.
Error handling’s tighter, the code is spry,
Models load smarter, let bugs pass by.
A hop, a skip, with features anew—
Wllama grows stronger, for all of you!

Note

⚡️ Unit Test Generation is now available in beta!

Learn more here, or try it out under "Finishing Touches" below.


📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 4147198 and 0ae3d8e.

⛔ Files ignored due to path filters (2)
  • src/multi-thread/wllama.wasm is excluded by !**/*.wasm
  • src/single-thread/wllama.wasm is excluded by !**/*.wasm
📒 Files selected for processing (3)
  • cpp/glue.hpp (1 hunks)
  • src/glue/messages.ts (2 hunks)
  • src/wllama.ts (4 hunks)
✅ Files skipped from review due to trivial changes (1)
  • src/glue/messages.ts
🚧 Files skipped from review as they are similar to previous changes (2)
  • cpp/glue.hpp
  • src/wllama.ts
⏰ 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: test (ubuntu-latest, 22)
✨ Finishing Touches
  • 📝 Generate Docstrings
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch xsn/fix_kv_rollback_fail

🪧 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.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

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.

@ngxson ngxson merged commit c267097 into master Jul 25, 2025
6 checks passed
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.

1 participant