deepseek-ai/Engram

Novel sparsity technique for LLMs using conditional memory and scalable lookup to reduce model size and improve efficiency.

Python
AI & Machine Learning
LLM Frameworks
Apache-2.0

3.8K

Stars

263

Forks

Jan 12, 2026

Created

Jan 14, 2026

Last Updated

Project Analytics

Stars Growth (1 Month)

+19

+0.5% change

Avg Daily Growth (1 Month)

+9.5

stars per day

Fork/Star Ratio (All Time)

6.9%

Normal engagement

Lifetime Growth

70.9

stars/day over 54 days

Stars Over Time

Forks Over Time

Open Issues Over Time

AI-Generated Tags

conditional-memory
sparsity
llm-optimization
lookup-tables
model-compression
deepseek

Comments (0)

Sign in to leave a comment or vote

Sign In

No comments yet. Be the first to comment!

Stay in the loop

Get weekly updates on trending AI coding tools and projects.