M.S. student, working on LLM Inference / Harness Engineering / Quantitative Trading / Diffusion Models.
- Core Developer @ KVCache.AI
- Contributor to KTransformers — heterogeneous LLM inference engine
- See our paper: KTransformers: Unleashing the Full Potential of CPU/GPU Hybrid Inference for MoE Models — SOSP 2025
- Contributor to KTransformers — heterogeneous LLM inference engine
- M.S. in Computer Science & Technology, BIT
- B.S. in Optics & Photonics, BIT
- International Collegiate Programming Contest (ICPC)
- Regional: 🏅 ×3 🥈 x3
- Asia East Continent Final (EC-Final): 🏅 x1 🥉 x1




