Pinned Loading

1. bwler bwler Public

   Official repo for BWLer: Barycentric Weight Layer

   Python 22 3

2. aioli aioli Public

   Aioli: A unified optimization framework for language model data mixing

   Jupyter Notebook 27 4

3. based based Public

   Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"

   Python 240 17

4. cartridges cartridges Public

   Storing long contexts in tiny caches with self-study

   Python 194 16

5. ThunderKittens ThunderKittens Public

   Tile primitives for speedy kernels

   Cuda 2.8k 180

6. minions minions Public

   Big & Small LLMs working together

   Python 1.2k 131