romnoj

ambientGPT

HVM

A massively parallel, optimal functional runtime in Rust

triton

Development repository for the Triton language and compiler

phoenix_live_view

Rich, real-time user experiences with server-rendered HTML

ScreenAI

Implementation of the ScreenAI model from the paper: "A Vision-Language Model for UI and Infographics Understanding"

OpenAdapt

AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] / Visual Language (VLMs)) Models

crates-tui

A TUI for exploring crates.io using Ratatui

corenet

CoreNet: A library for training deep neural networks

screen_qa

ScreenQA dataset was introduced in the "ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots" paper. It contains ~86K question-answer pairs collected by human annotators for ~35K screenshots from Rico. It should be used to train and evaluate models capable of screen content understanding via question answering.

reader

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

flash-attention-minimal

Flash Attention in ~100 lines of CUDA (forward pass only)

mlx-chat-app

Chat with MLX is a high-performance macOS application that connects your local documents to a personalized large language model (LLM).

llm.c

LLM training in simple, raw C/CUDA

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

classless-css

A list of classless CSS themes/frameworks with screenshots

valkey

A flexible distributed key-value datastore that supports both caching and beyond caching workloads.

gitbutler

The GitButler version control client, backed by Git, powered by Tauri/Rust/Svelte

hqq

Official implementation of Half-Quadratic Quantization (HQQ)

mlx-lora

raptor

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

open-interpreter

A natural language interface for computers

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

axolotl

Go ahead and axolotl questions

ZLUDA

CUDA on AMD GPUs

phoenix

AI Observability & Evaluation

VIRL

(ECCV 2024) Code for V-IRL: Grounding Virtual Intelligence in Real Life

ollama-rs

A Rust library allowing to interact with the Ollama API.

fastembed

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

pgvector

Open-source vector similarity search for Postgres

cidre

Apple frameworks bindings for rust