Pinned Loading

1. AutoAWQ AutoAWQ Public archive

   AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

   Python 2.3k 297

2. AutoAWQ_kernels AutoAWQ_kernels Public archive

   Cuda 79 23

3. OpenCoconut OpenCoconut Public archive

   OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.

   Python 175 23