Pinned Loading

1. FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.

   Python 337 20

2. minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.

   Jupyter Notebook 494 28

3. LLMProc: Unix-inspired runtime that treats LLMs as processes.

   Python 34 2

4. Codex-inspired local background agent

   Python 6

6. Anim·E, Anime Enhanced dalle mini

   Jupyter Notebook 40 3