Accelerating Encrypted AI with NVIDIA cuPQC
Today, Lattica is announcing support for NVIDIA cuPQC within the Lattica Platform and the HEAL runtime.
Read moreLATTICA BLOG
News & updates from the encrypted frontier.
Research, releases, partnerships, and the occasional behind-the-scenes note from the team building production-ready encrypted compute.
More from Lattica
6 posts
Measuring Encrypted AI and Vector Search with Workload-Level FHE Benchmarks
A new community benchmarking suite measures realistic workloads, not just primitives. Lattica has contributed to ML inference and encrypted vector search benchmarks, because shared reporting matters.
Read more
2nd FHE Landscape Survey
Lattica's 2nd FHE Landscape Survey highlights evolving commercial use cases, CKKS adoption, and practical signals for production FHE.
Read more
Technical Whitepaper
Two years of research and engineering, written down. How Lattica re-engineers FHE for accelerators, integrates with modern ML, and keeps keys on the client.
Read more
Announcing HEAL
HEAL is the integration layer that lets GPU, FPGA, and ASIC teams plug their hardware into Lattica's FHE stack. A reference CPU implementation, unit-test packs, the runtime, example transcripts, documentation, and direct support: everything a hardware team needs to ship a backend.
Read more
Emerging from Stealth
Lattica steps out of stealth with $3.25M in pre-seed funding to make Fully Homomorphic Encryption practical for AI workloads in the cloud.
Read more
2025 FHE Community Survey
Lattica surveyed cryptographers, engineers, and researchers to understand where FHE is headed. The responses reveal a mix of optimism and skepticism: progress is happening, but challenges remain.
Read more