Lists (5)
Stars
🏡 Open source home automation that puts local control and privacy first.
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Watch VR like a livestream. A comfortable way to enjoy VR video—no headset required, even if you're prone to motion sickness.
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to generate actions
Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.
A full list of GM commands for Vanilla WoW mangos private servers.
OpenAPI schema validator is a Python library that validates schema against OpenAPI Schema Specification v3.0 and v3.1
Lightweight repo with verifiable instructions for LLM training.
Warcraft III Peon voice notifications (+ more!) for Claude Code, Codex, IDEs, and any AI agent. Stop babysitting your terminal. Employ a Peon today.
Training library for Megatron-based models with bidirectional Hugging Face conversion capability
Compendium of over 50 benchmarks for evaluating AI agents, categorized into Function Calling & Tool Use, General Assistant & Reasoning, Coding & Software Engineering, and Computer Interaction.
Our library for RL environments + evals
Unofficial Evaluation for LLaDA2.0-mini-preview with LM-eval
Color schemes for default macOS Terminal.app
Auto get diffusion nlp papers in Axriv. More papers Information can be found in another repository "Diffusion-LM-Papers".
dInfer: An Efficient Inference Framework for Diffusion Language Models
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Minimalistic large language model 3D-parallelism training
A high performance general purpose code execution engine.
[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.
Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
[ICCV2025] LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds