deepseek-ai/Engram
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
The project lists 2 contributors on GitHub.
Use Cases & Benefits
- Implements a conditional memory module that enables scalable, constant-time lookup of static N-gram embeddings to augment large language models.
- Offers a new sparsity axis that balances neural computation and static memory, improving model efficiency and reasoning capabilities under fixed parameter budgets.
- Use for enhancing large language models with efficient memory retrieval to improve knowledge and reasoning tasks without increasing computational overhead.
- Use for research on scaling laws and capacity allocation between mixture-of-experts and memory modules in transformer architectures.
- Use for developing long-context training models that require effective static pattern reconstruction and deeper reasoning layers.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
Watch-outs
- No commits in the last six months (last push Jan 2026).
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
This repository contains the official implementation for the paper: Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models.
Abstract: While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup. To address this, we explore conditional memory as a complementary sparsity axis, instantiated via Engram, a module that modernizes classic $N$-gram embeddings for $\mathcal{O}(1)$ lookup.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
369+20
Open issues
24+4
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| anthropics/skills | 187.8K | +2.9K | 15 | — |
| DuarteSantos8/openGym | 19.7K | +2.4K | 60 | 2 days ago |
| shiyu-coder/Kronos | 47.0K | +2.3K | 16 | — |
| NationalSecurityAgency/ghidra | 98.2K | +2.3K | 64 | 14 days ago |
| microsoft/VibeVoice | 56.0K | +1.1K | 29 | — |
| deepseek-ai/Engram | 4.8K | — | 6 | — |
| Category median | 56.0K | +2.3K | 29 | — |
Also by deepseek-ai
Other repositories from this maintainer that GStars tracks
Discover Repositories
Search across tracked repositories by name or description