Building · Exploring · Transcending
Curated knowledge, tutorials, and insights worth passing on.
LLM Inference, AI Workshop, and more
vLLM · Quantization · Optimization
OS, Linux, Git, Claude Code, Deployment
Research papers and study materials
Interesting tools and useful discoveries
Where curiosity meets engineering — things I build and explore.
Optimizing large language model deployment — tensor parallelism, quantization, and memory management for production-scale systems.
Designing autonomous agents with persistent memory and decision-making. Stateful architectures for complex task execution.
Scalable applications with FastAPI and Next.js. API design, database architecture, and cloud infrastructure.
Beyond the screen — the things that make me who I am.
"The real voyage of discovery consists not in seeking new landscapes, but in having new eyes." — Marcel Proust
Learning, researching, and pushing the boundaries of what I know.