SuperMarioYL

中文版
# Hi, I'm Leo 👋

Typing SVG

AI Infrastructure Inference Acceleration Cloud Native

Building high-performance AI systems · LLM optimization · Multimodal inference · Scalable ML infrastructure


Blog Email Profile Views



🎯 Core Expertise

### 🏗️ AI Infrastructure Building scalable ML systems and training pipelines

PyTorch TensorFlow CUDA Triton

### ⚡ Inference Acceleration Optimizing model serving and reducing latency

vLLM TensorRT ONNX Quantization

### ☁️ Cloud Native Deploying and orchestrating at scale

Kubernetes Docker Ray Istio



🛠️ Tech Stack

Deep Learning Frameworks

Python PyTorch TensorFlow JAX

Inference & Optimization

CUDA TensorRT ONNX Runtime vLLM Triton Inference Server

Cloud Native & DevOps

Kubernetes Docker Ray Helm ArgoCD Prometheus

Languages & Tools

C++ Go Rust Git Linux

📊 View Detailed Language Statistics →
Language Stats



My Projects

Project Description
Bison Enterprise GPU Resource Billing & Multi-Tenant Management Platform

Technical Docs

Docs Description
Cloud Native Cookbook Cloud Native Technical Deep Dive
Inference Cookbook Inference Framework Deep Dive



📈 GitHub Stats

GitHub Contribution Graph



💭 About Me

Passionate about pushing the boundaries of AI performance.
When not optimizing inference pipelines, you'll find me cycling, exploring photography, or traveling.


© 2025 Leo · Powered by passion for AI and open source