Iceber Gu

Iceber/iouring-go

Provides easy-to-use async IO interface with io_uring

Iceber/grove

Kubernetes enhancements for Network Topology Aware Gang Scheduling & Autoscaling

Iceber/llm-d-async

Asynchronous Processor for Inference Gateway. Orchestrator of queues

Iceber/llm-d-inference-payload-processor

Inference payload processor for llm-d

Iceber/agentgateway

Next Generation Agentic Proxy for AI Agents and MCP servers

Iceber/vscode-imagegen

Native Image Generation for VS Code Agents

Iceber/llm-d-planner

Iceber/py-inference-scheduler

Python based inference-scheduler for Reinforcement Learning

Iceber/secure-inference

Iceber/llm-d-rl-time-slicing

Iceber/llm-d-fast-model-actuation

Kubernetes controllers for fast model actuation using vLLM sleep/wake and launcher-based model swapping

Iceber/video2e

Iceber/video-toolkit

Iceber/storyai-3d-director-desk

A browser-based 3D director desk demo built with React, Vite, and Three.js.

Iceber/c-ray

C-ray — X-ray your containers. See beneath the runtime.

Iceber/llm-d-kv-cache

Distributed KV cache scheduling & offloading libraries

Iceber/llm-d

Achieve state of the art inference performance with modern accelerators on Kubernetes

Iceber/llm-d-infra

repo for CI and infrastructure required to maintain llm-d org member repos

Iceber/llm-d-router

llm-d Router: The intelligent entry point for inference requests

Iceber/llm-d-modelservice

helm charts for deploying models with llm-d

Iceber/nvidia-container-toolkit

Build and run containers leveraging NVIDIA GPUs

Iceber/llm-d-workload-variant-autoscaler

Variant optimization autoscaler for distributed inference workloads

Iceber/ome

OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)

Iceber/velero

Backup and migrate Kubernetes applications and their persistent volumes

Iceber/pod-running-control

Iceber/openclaw-channel-github

Iceber/ai-forum

A Tieba-inspired community forum built with AI-assisted capabilities. In v1, users can create and join “Bars” (吧) to organize topics and interests, publish posts, and interact through threaded replies. AI is used to improve discovery, moderation, and content quality (without replacing human community culture).

Iceber/prompts

Iceber/wasmcloud-ollama

Iceber/promo-tools

Container and file artifact promotion tooling for the Kubernetes project