Xin Jin
Associate Professor
School of Computer Science
Peking University
Email: xinjinpku (at) pku (dot) edu (dot) cn
I am an Associate Professor in the
School of Computer Science at
Peking University.
I work on computer systems and networking. My research has received
USENIX NSDI Best Paper Award (2018) and USENIX FAST Best Paper Award
(2019).
Research
I am broadly interested in computer systems and networking. My research
currently focuses on designing and building systems for cloud computing and large language models.
Current Projects
- Serverless Computing
- Training and Serving Large Language Models
- Network Testing and Verification
- Disaggregated Storage with RDMA and DPUs
Recent Publications (All Publications)
- [SOSP 24] LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism
- [OSDI 24] DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
- [OSDI 24] dLoRA: Dynamically Orchestrating Requests and Adapters for LoRA LLM Serving
- [OSDI 24] Burstable Cloud Block Storage with Data Processing Units
- [NSDI 24] Jolteon: Unleashing the Promise of Serverless for Serverless Workflows
- [NSDI 24] Fast Vector Query Processing for Large Datasets Beyond GPU Memory with Reordered Pipelining
- [NSDI 24] MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
- [SOSP 23] Halfmoon: Log-Optimal Fault-Tolerant Stateful Serverless Computing
- [SOSP 23] Automated Verification of an In-Production DNS Authoritative Engine
- [SOSP 23] Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates
- [SIGCOMM 23] Ditto: Efficient Serverless Analytics with Elastic Parallelism
- [SIGCOMM 23] Klotski: Efficient and Safe Network Migration of Large Production Datacenters
- [SIGCOMM 23] Understanding the Micro-Behaviors of Hardware Offloaded Network Stacks with Lumina
- [SIGCOMM 23] XRON: A Hybrid Elastic Cloud Overlay Network for Video Conferencing at Planetary Scale
- [OSDI 23] AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
- [NSDI 23] Transparent GPU Sharing in Container Clouds for Deep Learning Workloads
- [NSDI 23] Fast, Approximate Vector Queries on Very Large Unstructured Datasets