Sparsity-aware deep learning inference runtime for CPUs

Official code for StoryMem: Multi-shot Long Video Storytelling with Memory

GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL

slime is an LLM post-training framework for RL Scaling.

🙌 OpenHands: AI-Driven Development

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, c…

Claude 3.5 Aided Design - use Claude to enhance modeling for 3D printing

Fix for sound card behavior on Huawei Matebook s14 / s16 on Ubuntu 22.04 / Fedora / Arch

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Open Source MicroPython Keyboard Firmware.

Micropython binding for the ESP32 DL AI vision models like face detection / recognition, imagenet classifier or pedestrian (human) detection

Script to produce colorized OpenSCAD models

Mirror only. Official repository is at https://git.zx2c4.com/wireguard-go

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

KeyV2: A Parametric Mechanical Keycap Library

LaTeX Thesis Template for Tsinghua University

MIDI file parser for Micropython, CircuitPython and Python

插件化、定制化、无广告的免费音乐播放器

The main repository of Starry-OS, which will assemble all kernel components into a kernel according to a certain configuration.

An ultra-lightweight Python interpreter that runs with only 4KB of RAM, zero dependencies. It is ready to use out of the box without any configuration required and easy to extend with C. Similar pr…

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

A high-throughput and memory-efficient inference and serving engine for LLMs

A MicroPython binding to the C++ kernels of PyTorch

Some CircuitPython tricks, mostly reminders to myself