- 🔥 Working on AI infrastructure, LLM systems, and GPU kernel optimization.
- 🚀 Optimizing high-performance kernels across NVIDIA and AMD GPUs.
- 🧠 Improving LLM inference frameworks, including vLLM, SGLang, and RTP-LLM.
- ⚙️ Focusing on GEMM, attention, and operator fusion.
- 🛠️ Open-source project: Atrex Kernel Agent.
- 🌐 Academic homepage: muse-coder.github.io.
- 📬 Reach me at 935522618@qq.com.