Optimizing inference proxy for LLMs

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

nanoGPT style version of Llama 3.1

Master programming by recreating your favorite technologies from scratch.

SGLang is a fast serving framework for large language models and vision language models.

PyTorch native finetuning library

Streaming server actions without the AI

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Examples in the MLX framework

Chat language model that can use tools and interpret the results

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Robust recipes to align language models with human and AI preferences

Random fake data generator written in go

Parallel S3 and local filesystem execution tool.

A golang library for building interactive and accessible prompts with full support for windows and posix terminals.

Guess structure of protobuf binary from raw data

Google Drive CLI Client

Go package for basic, fast, local reverse geocoding

A Zsh theme