clip : use smart pointers

[ngxson]

Make sure to read the contributing guidelines before submitting a PR

Summary by CodeRabbit

• New Features

  • Enhanced image batch processing, enabling more efficient handling and reliable dimension retrieval.

• Refactor

  • Upgraded memory management with automated resource cleanup, reducing the risk of memory issues.
  • Streamlined API naming and interfaces for improved clarity and usability.

• Bug Fixes

  • Resolved potential memory-related issues to boost overall system stability and performance.

[coderabbitai]

Caution

Review failed

The pull request is closed.

Walkthrough

The pull request refactors the image handling code by introducing C++ wrappers and smart pointer types for clip image objects. New custom deleter structures and unique pointers replace raw pointer usage in several components. The API is updated with new function signatures and getter functions, while the batch processing for images is augmented with initialization and dimension-query functions. Overall, the changes aim to streamline memory management and improve clarity across the code base.

Changes

Files	Change Summary
ex/llava/clip-impl.h	Added custom deleter structs (e.g., clip_image_u8_deleter, clip_image_f32_deleter), unique pointer wrappers (clip_image_u8_ptr, clip_image_f32_ptr), and batch structures for clip images.
ex/llava/clip.cpp, ex/llava/clip.h, ex/llava/llava.cpp	Transitioned raw pointers in clip_ctx to smart pointers; updated function signatures (using references instead of pointers); introduced new API functions for batch image processing and getters; refactored memory cleanup.
ex/llava/gemma3-cli.cpp	Modified eval_image to dynamically allocate a clip_image_f32_batch using clip_image_f32_batch_init() and adjusted related function calls to remove address-of operators, ensuring proper allocation and deallocation.

Sequence Diagram(s)

sequenceDiagram
    participant App as Application
    participant Batch as clip_image_f32_batch
    participant Pre as clip_image_preprocess
    participant Enc as clip_image_batch_encode

    App->>Batch: clip_image_f32_batch_init()
    App->>Pre: clip_image_preprocess(Batch)
    App->>Enc: clip_image_batch_encode(Batch)
    Enc-->>App: Encoded data
    App->>Batch: Automatic cleanup via smart pointers

Loading

Poem

I'm a rabbit hopping through the code,
Where pointers smartly lighten the load.
New deleters guard each image byte,
Batches of data spring into sight.
I nibble bugs with joy so bright,
Celebrating updates in pure delight! 🐰

---

📜 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 d3bd719 and 9f2920d.

📒 Files selected for processing (5)

• examples/llava/clip-impl.h (2 hunks)
• examples/llava/clip.cpp (31 hunks)
• examples/llava/clip.h (3 hunks)
• examples/llava/gemma3-cli.cpp (1 hunks)
• examples/llava/llava.cpp (6 hunks)

✨ Finishing Touches

• 📝 Generate Docstrings

---

🪧 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.
  • Generate unit testing code for this file.
  • 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 generate unit testing code for this file.
  • @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 generate unit testing code.
  • @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.

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 resolve resolve all the CodeRabbit review comments.
• @coderabbitai plan to trigger planning for file edits and PR creation.
• @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.