kcxain/Awesome-LLM4Kernel

LLM4Kernel: A Survey of Large Language Models for GPU Kernel Development

30
/ 100
Emerging

This resource provides a comprehensive overview for anyone interested in using Large Language Models (LLMs) to enhance GPU kernel development. It brings together a wide array of research papers, projects, and benchmarks, showing how LLMs can automate kernel generation, optimization, and verification. If you're a high-performance computing engineer, GPU programmer, or AI/ML researcher, this helps you stay current with the rapidly evolving field of LLM-assisted kernel development.

Use this if you need to understand the current landscape, key methodologies, and performance benchmarks for leveraging LLMs in GPU kernel development.

Not ideal if you are a beginner looking for a tutorial on how to write your first GPU kernel or directly implement an LLM for code generation without prior knowledge.

GPU Programming High-Performance Computing AI Compilers Kernel Optimization LLM for Code
No License No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 5 / 25
Community 7 / 25

How are scores calculated?

Stars

50

Forks

3

Language

License

Last pushed

Mar 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/kcxain/Awesome-LLM4Kernel"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.