Repository profile

re133 / sparse-memory-lm

A 21M-parameter LM with a 16.8M-row product-key memory: as good as a 114M dense model and runs with the table on an SSD. Triton kernels for ROCm and CUDA.

amd
language-model
memory-layers
product-key-memory
pytorch
rocm
triton

PythonView on GitHub

Repository overview

Public GitHub metrics and OpenPulse observations

GitHub stars16

Public forks1

Growth · 24h+0 stars

Growth · 7d+0 stars

Growth · 30d+16 stars

Star activity

Last 7 days

16 Oct4 observed days · gaps preserved19 Oct

Observed star growth

Samples or dated GitHub history

24h +0 stars Measured from observations 18 Oct 2026 → 19 Oct 2026

7d +0 stars GitHub history · as of 2026-10-17 11 Oct 2026 → 18 Oct 2026

30d +16 stars GitHub history · as of 2026-10-17 03 Oct 2026 → 18 Oct 2026