This month, our team at Zama released a new version of TFHE-rs (v1.1), alongside new versions of Concrete (v2.10), and Concrete ML (v1.9). With these releases, Zama continues to build its suite of products to make homomorphic encryption accessible, easy, and fast.

TFHE-rs v1.1

This new version of Zama's TFHE-rs brings several major improvements and new features for both GPU and CPU backends. The GPU backend now matches the CPU’s cryptographic parameters, reducing errors to under 2⁻¹²⁸ with minimal slowdown. Multi-GPU support lets users pick devices, enabling ~500 encrypted 64-bit additions/sec on 8×H100s. The CPU side now supports more scalar operations, enhancing efficiency and flexibility.

Read the full release blog post here

Concrete v2.10

This new version of Zama’s Concrete introduces a powerful new tool:  Concrete for Rust – an integration that brings Fully Homomorphic Encryption (FHE) directly to the Rust ecosystem. It’s a significant step toward production-grade FHE applications in modern systems programming.

‍Read the full release blog post here

Concrete ML v1.9

This new version of Zama’s Concrete ML introduces support for the TFHE-rs ciphertext format, enabling seamless integration of Concrete ML models into Rust-based FHE pipelines using TFHE-rs. Concrete ML v1.9 also brings performance improvements to the LoRA LLM fine-tuning protocol, and a new client SDK designed for building FHE-enabled browser and mobile applications.

Read the full release blog post here