LLM-guided CUDA kernel generation framework with correctness validation and roofline analysis
-
Updated
Dec 8, 2025 - Python
LLM-guided CUDA kernel generation framework with correctness validation and roofline analysis
BackBone AI is an innovative AI-driven code generation project designed to rapidly bootstrap robust and scalable backends using FastAPI and SQLAlchemy. It transforms natural language or structured schema definitions into production-ready Python code, focusing specifically on data persistence and API logic.
Useful classes and methods for researching code-generation by LLMs.
Benchmarking different Large Language Models on practical software development challenges
https://arxiv.org/abs/2505.02133 Enhancing LLM Code Generation: A Framework for Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency. Published in IEEE Xplore as part of the 2025 IEEE 19th International Conference on AICT.
Add a description, image, and links to the llm-code-generation topic page so that developers can more easily learn about it.
To associate your repository with the llm-code-generation topic, visit your repo's landing page and select "manage topics."