Starstruk Logo MarkStarstruk

0.1.0

QwenLM/Qwen3-VL0.1.0Jul 23, 2023by 1b5d

AI Summary

This initial release introduces Hugging Face compatibility for running popular models, upgrades the underlying inference engine to support Llama 2, and streamlines the Docker deployment to include a lightweight default image and a GPU-enabled image.

Key Highlights

  • Introduction of Hugging Face generic model support
  • Upgrade to llama.cpp for Llama 2 compatibility
  • Streamlined Docker image strategy (Lightweight + GPU)
  • General stability improvements and fixes

New Features

  • Hugging Face generic model integration
  • Llama 2 model support
  • GPU-accelerated Docker image
  • Lightweight Docker image

Full Release Notes

- Introducing Huggingface generic model, which can be used to run many popular models on HF
- Upgrade llama.cpp in order to run newer Llama models like Llama 2
- Streamline docker images down to 2 images: a default lightweight one, and a gpu enabled image with nvidia / cuda support
- General fixes and stability improvements