Welcome to my Github page! I am a student majoring in Electronic Information Engineering at CUIT.
๐ Things I am currently working on:
- Participating in InfiniCore operator library development
- Building custom inference engine with pure CUDA, MMA PTX, and CUTLASS implementations
- Deploying object detection models on RK3588 mobile platform
- Learning High Performance Computing (HPC)
โ Things I am challenging myself with:
- Flash-Attention implementation
- Developing custom inference engine with optimized CUDA operators
- Operator optimization using CUTLASS and PTX assembly
๐ป Recent interests:
- CUDA Programming & Kernel Optimization
- Large Vision Language Models (LLM)
- Parallel Computing & High Performance Computing
- Deep Learning Operator Development
- ๐ง InfiniCore: Contributing to operator library development
- โก Custom Inference Engine: Implementing operators using pure CUDA, MMA PTX, CUTLASS
- ๐ฑ Mobile AI Deployment: Object detection on RK3588 platform
