Yi-Feng Zhang
发表论文 2 篇
代表论文
- Janus: Realizing Practical Operator Parallelism for Latency-Sensitive DNN Inference on GPUs (2026 · ACM Transactions on Architecture and Code Optimization (TACO))
- Latency-Aware Orchestration for Multi-Agent LLM Workflows on Heterogeneous GPUs (2026)