Exploring Applications of GRPO

Coding assistant MCP for Claude Desktop

Pytorch script hot swap: Change code without unloading your LLM from VRAM

Python tool for converting files and office documents to Markdown.

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser & Trae AI (And other Open Sourced) System Prompts, Tools & AI Models.

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

Lightweight coding agent that runs in your terminal

Official repo for Learning to Reason for Long-Form Story Generation

Democratizing Reinforcement Learning for LLMs

Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"

ByteCheckpoint: An Unified Checkpointing Library for LFMs

VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework

NanoGPT-speedrunning for the poor T4 enjoyers

Learning FPGA, yosys, nextpnr, and RISC-V

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf

INVASE: Instance-wise Variable Selection . For more details, read the paper "INVASE: Instance-wise Variable Selection using Neural Networks," International Conference on Learning Representations (I…

A python library for self-supervised learning on images.

Build your own visual reasoning model

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

This repository is a curated collection of resources, tutorials, and practical examples designed to guide you through the journey of mastering CUDA programming. Whether you're just starting or look…

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

Custom PTX Instruction Benchmark

ETL, Analytics, Versioning for Unstructured Data

🦉 Data Versioning and ML Experiments

A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.

verl: Volcano Engine Reinforcement Learning for LLMs