Hi! I'm Hong Jae Hyeong, an AI Engineer from Korea.
I work on AI systems, backend services, and scalable infrastructure, always aiming to build reliable and efficient solutions.
I also enjoy contributing to the open source ecosystem and collaborating with developers to make tools and frameworks even better.
- [vllm] vLLM, DeepSeek V4 모델 성능 최적화: AITER MXFP4 BF16 백엔드 개선 (2026.06.26)
- [vllm] vLLM ROCm 환경에서 Shared-Expert Fusion을 통한 MoE 추론 성능 최적화 (2026.06.26)
- [onnxruntime] [ONNX Runtime] SGEMM의 함정에서 벗어나기: GQA 전용 GEMV 커널을 통한 디코딩 최적화 (2026.06.26)
- [논문리뷰] Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It (2026.06.25)
- [논문리뷰] When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models (2026.06.25)





