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

System for AI Education Resource.

Efficient and easy multi-instance LLM serving

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

浙大软院研究生毕业论文 Latex 模版2020

[USENIX ATC'24] The code for "SimEnc: A High-Performance Similarity-Preserving Encryption Approach for Deduplication of Encrypted Docker Images"

Understanding Differencing Algorithms for Mobile Application Updates

Kubernetes Scheduler Simulator

a unified scheduler for online and offline tasks

Heterogeneous AI Computing Virtualization Middleware

OCI Runtime Specification

Repository for design and specification of the Component Model

Write as Functions, Deploy as a Monolith or Microservice with WebAssembly

Collect papers about serverless computing research

SLEdge: a serverless runtime designed for the Edge.

High-performance stateful serverless runtime based on WebAssembly

论文写作与资料分享

cloud-native distributed storage

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and much more!

Lunatic is an Erlang-inspired runtime for WebAssembly

The WebAssembly Time Machine

wazero: the zero dependency WebAssembly runtime for Go developers

Shell-operator is a tool for running event-driven scripts in a Kubernetes cluster

A Kubernetes Resource Interface for the Edge

Learning Kubernetes, The Chinese Taoist Way

Zhejiang University Graduation Thesis LaTeX Template

A multi-sandbox container runtime that provides cloud-native, all-scenario multiple sandbox container solutions.

WebAssembly Micro Runtime (WAMR)