While having the ability to stream from a multitude of devices is not a new concept whatsoever, there are many variables that can interrupt your favorite show or movie on the go. Whether on a flight, ...

There was an error while loading. Please reload this page.

This is a port of BlinkDL/RWKV-LM to ggerganov/ggml. Besides the usual FP32, it supports FP16, quantized INT4, INT5 and INT8 inference. This project is focused on CPU, but cuBLAS is also supported.