Pinned Loading

1. AutoAWQ AutoAWQ Public

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

   Python 1.8k 222

2. AutoAWQ_kernels AutoAWQ_kernels Public

   Cuda 56 23

3. OpenCoconut OpenCoconut Public

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

   Python 80 10