Official repo for BWLer: Barycentric Weight Layer
Python 32 5
Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
Python 258 19
Storing long contexts in tiny caches with self-study
Python 339 44
Tile primitives for speedy kernels
Cuda 3.7k 331
Big & Small LLMs working together
Python 1.4k 150
Benchmarking Intelligence Efficiency of LM Inference
Python 95 15
Fast and Furious AMD Kernels
Code and paper reproductions for MLPs Are Hebbians
Kernels, of the mega variety :)
Ludwig benchmark
An open science effort to benchmark legal reasoning in foundation models