Running large language models on a single GPU for throughput-oriented scenarios.

Run Mixtral-8x7B models in Colab or consumer desktops

A QoE-Oriented Computation Offloading Algorithm based on Deep Reinforcement Learning (DRL) for Mobile Edge Computing (MEC) | This algorithm captures the dynamics of the MEC environment by integrating the Dueling Double Deep Q-Network (D3QN) model with Long Short-Term Memory (LSTM) networks.

ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory [COLM2025]

LLM Inference on consumer devices

dpdk infrastructure for software acceleration. Currently working on RX and ACL pre-filter

DPU-Powered File System Virtualization over virtio-fs

A collection of tests for the Open vSwitch HW offload.

A Dynamic Programming Offloading Algorithm for Mobile Cloud Computing

Monero hardware wallet protocol implementation for Trezor, agent

LeapIO: Efficient and Portable Virtual NVMe Storage on ARM SoCs (ASPLOS'20)

A framework for IoT devices to offload tasks to the cloud, resulting in efficient computation and decreased cloud costs.

A lightweight framework that enables serverless users to reduce their bills by harvesting non-serverless compute resources such as their VMs, on-premise servers, or personal computers.

The container-based cloud platform for mobile code offloading

Code for paper "Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI" (MobiCom'22)

Monero wallet Trezor integration documentation

No description provided.

Implementation of the RTSS'23 Best Student Paper Award paper Progressive Neural Compression for Adaptive Image Offloading under Timing Constraints

No description provided.

Fedora 42 KDE PLASMA Set UP On Lenovo Ideapad Gaming 3 with NVIDIA

基于 DPDK 和智能网卡的流量卸载试验. A flow offloading prototype base on DPDK and Mellanox/Nvidia SmartNIC.

Backend.AI Client Library for Python

Examples of using OpenMP offload with dgemm in the target region

DDS: DPU-optimized Disaggregated Storage

A "soft capture card" / Headless NDI® OBS offloading with HW transcoding

A Pandas-inspired data analysis project with lazy semantics and query-offloading to SQLite

Simulator for workflow scheduling and task offloading among mobile phones and edge clouds.

Deep Reinforcement Learning for Energy-Efficient Computation Offloading in Mobile-Edge Computing

An Activation Offloading Framework to SSDs for Faster Large Language Model Training

Offload object detection and ORBSLAM2 simultaneously from android client to servers via multipath.