GenAI Agent Framework, the Pydantic way

A safe and fast multi-producer, multi-consumer channel.

Circuit Breaker implemented in Go

GitHub Action to install CUDA

Fast and memory-efficient exact attention

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

Rust library for getting system information | also on https://codeberg.org/valpackett/systemstat

Easy to use RDMA API in Rust async

Go BPE tokenizer (Encoder+Decoder) for GPT2 and GPT3

A Go wrapper for GPT-3 token encode/decode. https://platform.openai.com/tokenizer

cross-platform Rust API for memory mapped IO

A cross-platform and safe Rust API to create and manage memory mappings in the virtual address space of the calling process.

An io_uring backed runtime for Rust

The `io_uring` library for Rust

An extensible, state of the art columnar file format. Formerly at @spiraldb, now an Incubation Stage project at LFAI&Data, part of the Linux Foundation.

Access to Anthropic's safety-first language model APIs via Go

You like pytorch? You like micrograd? You love tinygrad! ❤️

Token-Oriented Object Notation for Go – JSON for LLMs at half the token cost

Pure Go implementation of OpenAI's tiktoken tokenizer

Meta fork of the OG Jemalloc project

Support atomic operations on Arc itself

👨‍🚀 buzz, A small/lightweight statically typed scripting language

Build smaller, faster, and more secure desktop and mobile applications with a web frontend.

Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.

A curated collection of awesome README templates — contributions welcome

The Durable Task Framework is a lightweight, embeddable engine for writing durable, fault-tolerant business logic (orchestrations) as ordinary code.

Use io_uring from vanilla tokio.

A CLI tool to gather performance data and visualize using HTML graphs. Data from multiple collection runs can be viewed side-by-side, allowing for easy comparison of the same workload across differ…

High performance server-side application framework

The world’s fastest AI model gateway (450x less overhead than LiteLLM). Unified access to LLMs across endpoints (openAI, self-hosted, etc.) behind a single authentication layer - with API key gener…