• 🔭 I’m currently working on LLM inference architecture development
• 🌱 Specializing in multi-GPU parallelism and model acceleration
• 💻 Proficient in C++, Python, and CUDA programming
• 🚀 Experienced in optimizing large-scale model inference
• 🧠 Supporting various model architectures for efficient deployment
• 💡 Passionate about pushing the boundaries of AI efficiency