b8054
📦 llama-cppView on GitHub →
✨ 2 features🔧 1 symbols
Summary
This release adds support for Nemotron Nano 12B v2 VL models and simplifies related code. It also implements a change to pre-downsample position embeddings during GGUF conversion for fixed input size handling.
✨ New Features
- Added support for Nemotron Nano 12B v2 VL models (mtmd).
- Introduced pre-downsampling of position embeddings during GGUF conversion to enforce a fixed input size.