AIPython★ 130
cortsdine/LightVLM
LightVLM: VLM Optimization
Toolkit for quantization and cache optimization of vision-language models, accelerating inference and reducing memory usage.
// KEY FEATURES
- Weight quantization to 4-bit without significant accuracy loss
- Attention layer cache optimization for faster text generation
- Support for popular VLMs: CLIP, BLIP, Flamingo via a simple API
- PyTorch integration and ONNX export for Edge deployment
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram