YaoZengzeng/scripts
All the scripts which I think is useful will put on here.
AI Infra/Service Mesh/Kubernetes Ecosystem/Huaweier/ZJUer/HUSTer
All the scripts which I think is useful will put on here.
Some Analysis Articles Of Kubernetes Ecosystem Writing By My Own Research
AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
LeaderWorkerSet: An API for deploying a group of pods as a unit of replication
A multi-sandbox container runtime that provides cloud-native, all-scenario multiple sandbox container solutions.
☁️♮🏛 This repo contains several documents related to the operation of the CNCF. File non-technical issues related to CNCF here.
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.
SGLang is a fast serving framework for large language models and vision language models.
A high-throughput and memory-efficient inference and serving engine for LLMs
Systematic and comprehensive benchmarks for LLM systems.
Cost-efficient and pluggable Infrastructure components for GenAI inference
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Manages Envoy Proxy as a Standalone or Kubernetes-based Application Gateway
LangChain for Go, the easiest way to write LLM-based programs in Go
Get up and running with Llama 3.3, Mistral, Gemma 2, and other large language models.
🪿 LinGoose is a Go framework for building awesome AI/LLM applications.
Kubernetes integration for OVN
High Performance ServiceMesh Data Plane Based on Programmable Kernel
CLI tool for spawning and running containers according to the OCI specification
Kmesh website and documentation repo
An experimental implementation of the `ztunnel` component of ambient mesh
Istio governance material.
API definitions for the Istio project
Production-Grade Container Scheduling and Management
Deploys many lightweight XDS clients to generate load on an XDS server (Pilot)