Pinned Loading

1. flex-nano-vllm flex-nano-vllm Public

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

   Python 254 12

2. minLoRA minLoRA Public

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

   Jupyter Notebook 474 28

3. llmproc llmproc Public

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

   Python 32 2

4. kodx kodx Public

   Codex-inspired local background agent

   Python 5

5. claude-code-system-prompts claude-code-system-prompts Public

   JavaScript 13 2

6. anim_e anim_e Public

   Anim·E, Anime Enhanced dalle mini

   Jupyter Notebook 42 3