Lists (1)
Sort Name ascending (A-Z)
Stars
Productive, portable, and performant GPU programming in Python.
Finding Atari 2600 games in randomly generated data
TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle
An experimental operating system fully written in Rust, with a unikernel design, cooperative scheduling and a security model based on WASM sandboxing.
Port of the OpenCascade CAD library to JavaScript and WebAssembly via Emscripten.
A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
[CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R
A FlashAttention implementation for JAX with support for efficient document mask computation and context parallelism.
MLGym A New Framework and Benchmark for Advancing AI Research Agents
Simple, efficient, open-source package for Simultaneous Localization and Mapping
π€ LeRobot: Making AI for Robotics more accessible with end-to-end learning
Fully documented and annotated source code for Elite on the Commodore 64
Ultimate Commodore 64 Reference: ROM Disassembly, Memory Map, ...
Accelerating your LLM training to full speed! Made with β€οΈ by ServiceNow Research
AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
π§ Compare how Agent systems perform on several benchmarks. ππ
Neural signal propagation atlas (Randi et al.), genome (WormBase), single-cell transcriptome (Taylor et al.), neuropeptide/GPCR deorphanization (Beets et al.), monoaminergic connectome (Bentley et β¦
ππͺ BrowserGym, a Gym environment for web task automation
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
DeepSeek LLM: Let there be answers
Automatically split your PyTorch models on multiple GPUs for training & inference
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
Base code for the Dingo quadruped; modified from Stanford Pupper and Notspot repositories. Includes integration with ROS Noetic and a simulation of the Dingo