🧑‍💻 Apply now to build the next generation of enterprise multi-agent systems. AI agents are becoming useful across enterprise work including planning, coding, research, compliance, finance, support, ...

mx-llama.cpp is a fork of llama.cpp focused on multi-GPU optimization, with single-GPU and speculative-decoding work alongside. The optimizations are backend-generic; the kernel-level tuning targets ...

The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud.