Lists (3)
Stars
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
LiteLinear is a drop-in inference acceleration: compress nn.Linear layers via calibration-aware low-rank decomposition + quantization
vhnatyk / icicle
Forked from ingonyama-zk/iciclea GPU Library for Zero-Knowledge Acceleration
TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
A library implementing GPU-accelerated cryptographic functionality for the zkSync prover.
Boojum, the scariest SNARK implementation.
A zkVM for Decentralized Private Computations (DPC)
A hardware acceleration library for compute intensive cryptography 🧊
Danksharding Builder with GPU acceleration
Alternative rust compiler (re-implementation)
blaze is a Rust library for ZK acceleration on Xilinx FPGAs.
Resilient network services with mobile Xamarin apps
A Decentralized Operating System for ZK Applications
A curated list of ZK/FHE resources and links. 👇 Click below for the website version.
Rate Limiting (debounce, throttle) for C# Portable Class Library
UI-responsive touch effects for Xamarin.Forms
Fingerprint authentication example in Xamarin.Forms.