OSS RL environment + evals toolkit

An educational resource to help anyone learn deep reinforcement learning.

Verify Precision of all Kimi K2 API Vendor

High-Resolution Image Synthesis with Latent Diffusion Models

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

NanoGPT (124M) in 3 minutes

verl: Volcano Engine Reinforcement Learning for LLMs

Quantized LLM training in pure CUDA/C++.

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. All in a modern, AI-native editor.

Dion optimizer algorithm

Official code release for "SuperBPE: Space Travel for Language Models"

Convert your language model into a byte-level one!

A minimal implementation of DeepMind's Genie world model

A lightweight, local-first, and free experiment tracking library from Hugging Face 🤗

ScaleCUA is the open-sourced computer use agents that can operate on corss-platform environments (Windows, macOS, Ubuntu, Android).

This repository contains companion software for the Colfax Research paper "Categorical Foundations for CuTe Layouts".

Official repository of the paper 'AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios'.

Efficient Triton Kernels for LLM Training

GPU programming related news and material links

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Practical low-rank gradient compression for distributed optimization: https://arxiv.org/abs/1905.13727

Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)

PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP

CUDA GPU Benchmark