CYJiang

googs1025/kvcached

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

googs1025/googs1025

googs1025/tilelang

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

googs1025/hiroute

A local-first routing and coordination engine for long-running agent work.

googs1025/musa-learning-notes

学摩尔线程 MUSA SDK 的学习记录

googs1025/openclaw-operator

Kubernetes operator for deploying and managing OpenClaw AI agent instances with production-grade security, observability, and lifecycle management.

googs1025/flashinfer

FlashInfer: Kernel Library for LLM Serving

googs1025/nanoeuler

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

googs1025/colibri

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

googs1025/clean-code-reviewer-skills

基于《代码整洁之道》《架构整洁之道》《程序员修炼之道》三本经典的中文代码审查 Claude Code Skill

googs1025/llm-wiki

googs1025/CUDALibrarySamples

CUDA Library Samples

googs1025/dragonfly

Delivers efficient, stable, and secure data distribution and acceleration powered by P2P technology, with an optional content‑addressable filesystem that accelerates OCI container launch.

googs1025/llm-d-fast-model-actuation

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

googs1025/nephio

Nephio is a Kubernetes-based automation platform for deploying and managing highly distributed, interconnected workloads such as 5G Network Functions, and the underlying infrastructure on which those workloads depend.

googs1025/llama.cpp

LLM inference in C/C++

googs1025/anolisa

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture)

googs1025/ai-gateway

Envoy AI Gateway is an open source project for using Envoy Gateway to handle request traffic from application clients to Generative AI services.

googs1025/kthena

googs1025/cuda-samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

googs1025/llm-d-router

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

googs1025/llm-d

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

googs1025/WeKnora

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

googs1025/llm-d-autoscaling

Variant optimization autoscaler for distributed inference workloads

googs1025/gpu-perf-engineering-resources

A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.

googs1025/speculators

A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

googs1025/agentic-api

Stateful API logic for agentic applications using vLLM

googs1025/AVE

AVE 是面向安全运营的多源漏洞知识库，统一 AVE 编号并输出结构化 TOML，同时整理和校验公开 PoC/EXP 资产，支持按严重等级快速筛选高价值漏洞。漏洞爬取与梳理的代码和逻辑暂未开源。

googs1025/vLLM-SGLang-book

vLLM 与 SGLang： 大模型高效推理双引擎实战配套代码

googs1025/hwpoc

护网漏洞情报库 · 0day/1day/nday 漏洞数据 · 原腾讯文档迁移 · Issue 提交 · TOML 源数据