cryptopoly/ChaosEngineAI

Local AI workstation — discover, run, chat, benchmark, and generate images from open-weight models. DFlash/DDTree speculative decoding, TurboQuant & TriAttention cache compression strategies, MLX + llama.cpp + vLLM + MTPLX backends.

🎬 Media Creation ✓ Commercial OK ★ 24Python

↗ Source

Commercial license

✓ Commercial OKApache-2.0

可商用，通常只需保留著作權聲明/授權條款

Topics

aiapple-siliconcache-compressiondesktop-appdflashggufhuggingfaceimage-generationllama-cppllmlocal-aimachine-learning