C++ SDK that provides resources for implementing and validating Trusted Computing Solutions on NVIDIA hardware

WebAssembly (Wasm) arch support for the Linux kernel

Build userspace NVMe drivers and storage applications with CUDA support

A machine learning accelerator core designed for energy-efficient AI at the edge.

SMT Modeling for Ghidra's PCODE

List system USB buses and devices. A modern cross-platform lsusb that attempts to maintain compatibility with, but also add new features

Artifact for "Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing"

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Circuit diagrams and firmware source code for Gboard DIY keyboards

This is the top-level repository for the Accel-Sim framework.

Microsandbox — Self-Hosted Plaform for Secure Execution of Untrusted User or AI-Generated Code

A Rust-based embedded operating system designed to enable memory-safe, robust, and responsive embedded applications.

Pie: Programmable LLM Serving

Hugin. The type-1 hypervisor on aarch64.

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Lightweight coding agent that runs in your terminal

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]

A deep dive into the ACPI.sys DPC latency problems on Asus ROG laptops

Python Frontend to LLVM IR for eBPF programs in Pure Python

Fast Multimodal LLM on Mobile Devices

Deduplicating archiver with compression and authenticated encryption.

Set of tools to assess and improve LLM security.

Writing a hypervisor in 1,000 lines.

Rex is a safe and usable kernel extension framework that allows loading and executing Rust kernel extension programs in the place of eBPF.