HazyResearch

Pinned Loading

1. bwler bwler Public

   Official repo for BWLer: Barycentric Weight Layer

   Python 33 5

2. based based Public

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

   Python 258 20

3. cartridges cartridges Public

   Storing long contexts in tiny caches with self-study

   Python 344 45

4. ThunderKittens ThunderKittens Public

   Tile primitives for speedy kernels

   Cuda 3.8k 339

5. minions minions Public

   Big & Small LLMs working together

   Python 1.4k 156

6. intelligence-per-watt intelligence-per-watt Public

   Benchmarking Intelligence Efficiency of LM Inference

   Python 103 15