cd /news/artificial-intelligence/ul-smf-open-source-linear-complexity… · home topics artificial-intelligence article
[ARTICLE · art-100023] src=github.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

UL-SMF – Open-source linear-complexity KV-cache compression

Lawrence Architectures released UL-SMF, an open-source KV-cache compression fabric that reduces memory footprint by up to 384x with over 94% semantic retention, addressing the memory bottleneck in long-context Transformer inference. The dual-licensed software (AGPLv3 for non-commercial use, commercial license for proprietary deployments) dynamically maps any model hidden dimension using Finite Scalar Quantization and 16-dimensional latent mapping, achieving 99.7% memory savings per block.

read1 min views7 publishedAug 17, 2026
UL-SMF – Open-source linear-complexity KV-cache compression
Image: Michielbdejong (auto-discovered)

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 Finite Scalar Quantization (FSQ) with dynamic 16-dimensional latent mapping, UL-SMF compresses Key-Value (KV) cache tensors by up to 384x while maintaining >94% semantic retention.

UL-SMF is dual-licensed:

Open Source (AGPLv3): Free for non-commercial research, academic use, and open-source projects.*Note: The AGPLv3 license requires any network-accessible service using this software to open-source its entire backend application code.*Commercial Enterprise License: Required for proprietary commercial deployments, closed-source SaaS platforms, and enterprise data center infrastructure. Commercial licenses grant full rights without AGPLv3 copyleft restrictions, plus integration support.

📩 For Enterprise Licensing Inquiries: inquiries@lawrencearchitectures.com

Metric Raw FP32 Cache UL-SMF 16D Latent Improvement
VRAM Footprint (4096 tokens)
48.00 MB 0.12 MB 384x Reduction
VRAM Saved / Block
47.88 MB
99.7% Memory Saved
Semantic Retention
100% 94.15% - 95.84%
Cosine Similarity
Pipeline Latency
~14.1 ms - 19.6 ms
CUDA Event Verified

UL-SMF dynamically maps any model hidden dimension (Mistral, Llama, Qwen, etc.) on-the-fly using orthogonal projection:

import torch
from ul_smf import UniversalLatentBridge

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
oracle_core = torch.jit.load("aegis_kv_oracle_core.pt", map_location=device)
oracle_core.eval()

ul_smf_bridge = UniversalLatentBridge(core_module=oracle_core, core_dim=3072).to(device)

kv_cache_tensor = torch.randn(1, 32, 4096, device=device)
reconstructed_cache, compressed_latents = ul_smf_bridge(kv_cache_tensor)

print(f"Compressed down to latent space: {compressed_latents.shape}")
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @lawrence architectures 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ul-smf-open-source-l…] indexed:0 read:1min 2026-08-17 ·