Skip to content

Conversation

@sgonorov
Copy link
Contributor

Fix const cast in phi3 qwen and minicpm

@Wovchena Wovchena requested a review from Copilot November 25, 2025 14:33
@Wovchena Wovchena enabled auto-merge November 25, 2025 14:33
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull request overview

This PR addresses const_cast issues when constructing ov::Tensor objects in visual language processing modules. The changes ensure proper const-correctness when passing data pointers to tensor constructors.

  • Added const_cast to pointer arguments when constructing ov::Tensor objects
  • Reformatted tensor constructor calls for improved readability
  • Applied consistent fixes across phi3_vision, qwen2vl, and minicpm modules

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.

File Description
src/cpp/src/visual_language/qwen2vl/classes.cpp Added const_cast for image data pointers and reformatted tensor constructors
src/cpp/src/visual_language/phi3_vision/classes.cpp Added const_cast for token data pointers in placeholder processing
src/cpp/src/visual_language/minicpm/classes.cpp Added const_cast for slice data pointer and reformatted tensor constructor

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

@github-actions github-actions bot added category: image generation Image generation pipelines category: LLM LLM pipeline (stateful, static) category: whisper Whisper pipeline category: speculative decoding Speculative decoding no-match-files category: speech generation labels Nov 25, 2025
@github-actions github-actions bot added category: continuous batching Continuous batching category: sampling Sampling / Decoding algorithms labels Nov 26, 2025
@Wovchena Wovchena added this pull request to the merge queue Nov 26, 2025
Merged via the queue into openvinotoolkit:master with commit 65b9356 Nov 26, 2025
122 of 124 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

category: continuous batching Continuous batching category: image generation Image generation pipelines category: LLM LLM pipeline (stateful, static) category: sampling Sampling / Decoding algorithms category: speculative decoding Speculative decoding category: speech generation category: visual language Visual language pipeline category: whisper Whisper pipeline no-match-files

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants