Goldezstevie

Goldezstevie/amd-multimodal-lab

Vision-Language Models on AMD GPUs — LLaVA, MiniGPT-4, Idefics on ROCm 🚀

11 stars 0 forks 11 watchers Python MIT License

multimodal open-source python rocm vision-language

2 Open Issues Need Help Last updated: Jul 9, 2026

Open Issues Need Help

View All on GitHub

Bug: LLaVA inference slow on first run 12 days ago

bug enhancement help wanted good first issue

Goldezstevie/amd-multimodal-lab

11

Vision-Language Models on AMD GPUs — LLaVA, MiniGPT-4, Idefics on ROCm 🚀

Python

#multimodal#open-source#python#rocm#vision-language

Feature: Add image captioning batch mode 20 days ago

bug enhancement help wanted good first issue question

Goldezstevie/amd-multimodal-lab

11

Vision-Language Models on AMD GPUs — LLaVA, MiniGPT-4, Idefics on ROCm 🚀

Python

#multimodal#open-source#python#rocm#vision-language