Starred repositories
🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton
About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]
Framework for running AI locally on mobile devices and wearables. Hardware-aware C/C++ backend with wrappers for Flutter & React Native. Kotlin & Swift coming soon.
An open-source implementaion for fine-tuning Qwen2-VL and Qwen2.5-VL series by Alibaba Cloud.
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
Anthropic's Interactive Prompt Engineering Tutorial
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
The simplest, fastest repository for training/finetuning small-sized VLMs.
small auto-grad engine inspired from Karpathy's micrograd and PyTorch
Efficient Triton Kernels for LLM Training
FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser, Trae AI & Cluely (And other Open Sourced) System Prompts, Tools & AI Models.
Lightweight coding agent that runs in your terminal
A deep-dive on the entire history of deep-learning
Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
verl: Volcano Engine Reinforcement Learning for LLMs
Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.
An example starter repo for Python projects
Compiling useful links, papers, benchmarks, ideas, etc.
Build your own visual reasoning model
Official implementation of UnifiedReward & UnifiedReward-Think
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
Rapid fuzzy string matching in Python using various string metrics
An extremely fast Python package and project manager, written in Rust.
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.