REAP: Router-weighted Expert Activation Pruning for SMoE compression

A community database for the problems on the erdosproblems.com site

Implementation for "Model Compression with Exact Budget Constraints via Riemannian Manifolds"

Convert PDF to markdown + JSON quickly with high accuracy

A statusbar for pi.dev agents

The open source coding agent.

Efficient non-uniform quantization with GPTQ for GGUF

A high-throughput and memory-efficient inference and serving engine for LLMs

LLM training in simple, raw C/CUDA

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

FedCCL: Federated Clustered Continual Learning Framework for Privacy-focused Energy Forecasting

LLM inference in C/C++

Tensors and Dynamic neural networks in Python with strong GPU acceleration

A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.

A library for efficient similarity search and clustering of dense vectors.

High performance self-hosted photo and video management solution.

Ruby on Rails