Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Like deepseek-ai/Engram, 0 likes 0 Bookmark deepseek-ai/Engram, 0 bookmarks 0 ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, verified on llama.cpp GGUF (Qwen3.8-Flash-Next).
Like fulvian/engraft-ngram, 0 likes 0 Bookmark fulvian/engraft-ngram, 0 bookmarks 0 The official repo of the paper: $delta$-mem: Efficient Online Memory for Large Language Models
Like declare-lab/delta-Mem, 0 likes 0 Bookmark declare-lab/delta-Mem, 0 bookmarks 0 The official implementation of the paper "MLP Memory: A Retriever-Pretrained Memory for Large Language Models". (ICLR 2026)
Like LUMIA-Group/MLPMemory, 0 likes 0 Bookmark LUMIA-Group/MLPMemory, 0 bookmarks 0 Official repository for MemT-1.0
Like MemTensor/MemT-1.0, 0 likes 0 Bookmark MemTensor/MemT-1.0, 0 bookmarks 0 This repositories contains the reference implementation for the Sparse Delta Memory paper.More precisely, it contains the model definition as well as triton and cuda kernels for the Sparse Delta Memory layer.
Like facebookresearch/sparse-delta-memory, 0 likes 0 Bookmark facebookresearch/sparse-delta-memory, 0 bookmarks 0 Hybrid Transformer with Online RNN Memory for Neocortex Memory.
Like xiaol/Multi-state-RWKV-online-memory, 0 likes 0 Bookmark xiaol/Multi-state-RWKV-online-memory, 0 bookmarks 0 Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
Like Wenyueh/MinivLLM, 0 likes 0 Bookmark Wenyueh/MinivLLM, 0 bookmarks 0 Breaking the quadratic memory barrier in AI
Like eelbaz/mLattice, 0 likes 0 Bookmark eelbaz/mLattice, 0 bookmarks 0