booster
Booster - open accelerator for LLM models. Better inference and debugging for AI hackers
- 170
- C++
- 2 y ago
Booster - open accelerator for LLM models. Better inference and debugging for AI hackers
Run your own AI at home, in one single executable: llama.cpp on your GPU (installed automatically, or compiled for your card), ExLlama, or any OpenAI-compatible API. Memory, agent tools, scheduled tasks, access from your phone. Windows, macOS, Linux.
Skill для Hermes / Claude Code / Codex-агентов: автоматический выбор и настройка LLM inference engine под железо, модель и workload — MLX, llama.cpp, ExLlama, vLLM, SGLang, TensorRT-LLM.