liventruth/UL-SMF-Cache-Compression

The Unified Latent-State Memory Fabric (UL-SMF) is a hardware-software co-designed memory compression fabric that solves the memory bottleneck in long-context Transformer inference. By combining FSQ with dynamic 16-dimensional latent mapping, UL-SMF compresses Key-Value (KV) cache tensors by up to 384x while maintaining >94% semantic retention.

13 best points · 1 comments · 1 Hacker News post · 10 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: UL-SMF – Open-source linear-complexity ~300x KV-cache compression (13 points, 1 comments, by liventruth, 2026-08-17)