Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
FHEVM, a full-stack framework for integrating Fully Homomorphic Encryption (FHE) with blockchain applications
Zama's Homomorphic Processing Unit implementation on FPGA
A browser based Pokémon fangame heavily inspired by the roguelite genre.
An autonomous agent that conducts deep research on any data using any LLM providers
A pytorch quantization backend for optimum
Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
NVIDIA Federated Learning Application Runtime Environment
aider is AI pair programming in your terminal
A Solidity library for interacting with fhevm.
<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox.
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".
Brevitas: neural network quantization in PyTorch
Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.
Exploring finetuning public checkpoints on filter 8K sequences on Pile
Zama Bounty Program: Contribute to the FHE space and Zama's open source libraries and get rewarded 💰
TFHE-rs: A Pure Rust implementation of the TFHE Scheme for Boolean and Integer Arithmetics Over Encrypted Data.
Privacy-preserving XGBoost Inference
Crypto-currency software to manage libre currency such as Ğ1. Mirror of:
Train Gradient Boosting models that are both high-performance *and* Fair!
High performance self-hosted photo and video management solution.
An easy way to extract information from documents
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.