Pinned Loading

1. local-engine-router local-engine-router Public

   Single-port OpenAI/Ollama-compatible proxy that auto-swaps a memory-constrained GPU between local inference engines by requested model.

   Python 2

2. llmtop llmtop Public

   An nvtop for local LLM inference: zero-config autodiscovery of vLLM, llama.cpp, Ollama, TGI, SGLang + live GPU and serving metrics in a Textual TUI. Unified-memory (GB10/Jetson) aware. MIT.

   Python