Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

10 Open Issues Need Help Last updated: Jul 28, 2026

Open Issues Need Help

View All on GitHub
good first issue category: speculative decoding

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

C++

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

C++
good first issue

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

C++
good first issue category: C API

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

C++
good first issue category: LoRA

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

C++
good first issue category: JS API

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

C++

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

C++
good first issue

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

C++

AI Summary: This issue aims to improve GenAI code style by implementing basic git-based code checks. It involves configuring the `pre-commit` Python module to run `check-merge-conflict` and `check-json` from a specified list of checks, explicitly excluding language-specific ones. The final step is to fix any detected issues, with specific exceptions for the root `README.md` and an auto-generated Python file.

Complexity: 2/5
good first issue

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

C++

AI Summary: The task requires extending the existing OpenVINO GenAI C++ API to include support for the WhisperPipeline, enabling easier integration with other languages like .NET via P/Invoke. This involves adding a C API wrapper for the WhisperPipeline's functionality, mirroring the existing C API for LLMPipeline.

Complexity: 4/5
good first issue

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

C++