Sponsors
1
Speakers
12
Attendees
150
LLM Infra and Distributed Inference is a conference focused on efficient inference technologies and frameworks for large language models. It features presentations by leading academics and industry experts on topics like heterogeneous inference technology, lightweight high-performance inference frameworks, open source serving frameworks, and new AI computation architectures. The event gathers AI researchers, developers, and industry practitioners aiming to advance scalable and efficient AI model serving.
Core Developer
SGLang
Vice Director, Head of Large Model Tool Team
SenseTime Technology, SenseTime Research Institute
Senior Technical Director, AI Computing Architecture
NVIDIA
PhD Student, Core Maintainer
Tsinghua University, vLLM
Representative
Ritual Foundation
Associate Professor
Tsinghua University
Ritual Foundation
高级技术总监
英伟达AI计算架构部门 (NVIDIA)
博士生, vLLM Core Maintainer
清华大学
副教授
清华大学
SGLang核心开发者
副总监,大模型工具体系团队负责人
商汤科技(SenseTime)
💡 Looking for sponsorship opportunities? Our platform provides detailed sponsor contact information and pricing data to help you make informed partnership decisions.