FlashMLA: Efficient MLA Decoding Kernel for Hopper GPUs

This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

[ICLR2025] IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis

A sparse attention kernel supporting mix sparse patterns

Official PyTorch implementation for "Large Language Diffusion Models"

SWE Arena

Based on the R1-Zero method, using rule-based rewards and GRPO on the Code Contests dataset.

A python program that turns an LLM, running on Ollama, into an automated researcher, which will with a single query determine focus areas to investigate, do websearches and scrape content from vari…

HumanLayer enables AI agents to communicate with humans in tool-based and async workflows. Guarantee human oversight of high-stakes function calls with approval workflows across slack, email and mo…

verl: Volcano Engine Reinforcement Learning for LLMs

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

[NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Training Large Language Model to Reason in a Continuous Latent Space

The Campsite monorepo

PyTorch implementation of PerCo (Towards Image Compression with Perfect Realism at Ultra-Low Bitrates, ICLR 2024)

Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

Official repository for our work on micro-budget training of large-scale diffusion models.

Fast, Modern, Memory Efficient, and Low Precision PyTorch Optimizers

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

A Telegram bot to recommend arXiv papers

a family of versatile and state-of-the-art video tokenizers.

An Open Source Toolkit For LLM Distillation

Source code for <Large language models surpass human experts in predicting neuroscience results>