tf-engram-02d7bc71·1 events·first seen Aliases: TF-Engram
TF-Engram is a train-free memory system for LLMs that constructs phrase-specific semantic memory offline from external corpora and stores it across a GPU–DRAM–SSD hierarchy, avoiding the hash-collision problems of prior engram-style approaches. The system uses Early-Exit Guided Predictive Prefetching to hide external-memory latency during autoregressive decoding. Evaluated on Qwen3-0.6B, it improves average downstream score from 57.6 to 59.4, outperforming both the frozen backbone and a parameter-matched LoRA baseline, while substantially reducing GPU memory demand.