When to Reason: Semantic Router for vLLM
- Chen Wang
- Xunzhuo Liu
- et al.
- 2025
- NeurIPS 2025
Publications
5 results for Junchen Jiang
Networking for Stateful LLM Inference
- Junchen Jiang
- Yuhan Liu
- et al.
- 2025
- SIGCOMM 2025
Scalable and Efficient LLM Serving with the vLLM Production Stack
- Junchen Jiang
- Yue Zhu
- 2025
- OSSNA 2025
Towards Optimal Preemptive GPU Time-Sharing for Edge Model Serving
- Zhengxu Xia
- Yitian Hao
- et al.
- 2023
- MIDDLEWARE 2023
DEFT: SLO-Driven Preemptive Scheduling for Containerized DNN Serving
- Yitian Hao
- Wenqing Wu
- et al.
- 2023
- NSDI 2023