09:00-09:20 - Welcome & Opening Remarks
Matt White | The Linux Foundation
09:20-09:40 - Running Large Models on Any AI Chip: PyTorch + Open-Source Stack (FlagOS) for Architecture-Free Deployment
Yonghua Lin | Beijing Academy of Artificial Intelligence (BAAI)，Vice President and Chief Engineer
09:40-10:00 - Diving in Hugging Face Hub; Share Your Model Weights on the #1 AI Hub, Home of 700k+ PyTorch Models
Tiezhen Wang | Hugging Face，Engineer
10:00-10:20 - verl: An Open Source Large Scale LLM RL Framework for Agentic Tasks
Yuxuan Tong | Bytedance，Researcher
10:20-10:30 - PyTorch in China: Community Growth, Localization, and Interaction
Zesheng Zong | Huawei，Senior Software Engineer
11:00-11:30 - torch.accelerator: A Unified, Device-Agnostic Runtime API for Stream-Based Accelerators
Yu Guangye | Intel，AI Framework Engineer
11:30-11:50 - vLLM: Easy, Fast, and Cheap LLM Serving for Everyone
KaiChao You | Tsinghua University，Student
11:50-12:00 - A torch.fx Based Compression Toolkit Empowered by torch_musa
Fan Mo | Moore Threads，Machine Learning Engineer
12:00-14:00 - Lunch (Attendees On Own)
14:00-14:20 - Efficient Training of Video Generation Foundation Model at ByteDance
Xiaonan Nie | ByteDance Seed，Research Scientist in Machine Learning System
Yong Li | Bytedance，Research Scientist in MLSys
14:20-14:40 - torch.compile Practice and Optimization in Different Scenarios
Yichen Yan | Alibaba Cloud，Senior Engineer
14:40-15:00 - PyTorch in Production: Boosting LLM Training and Inferencing on Ascend NPU
Jiawei Li | Huawei Technologies Co., Ltd.，Staff Engineer
15:00-15:20 - Galvatron: An Automatic Distributed Training System for Efficient Large-Scale Transformer Training
Fangcheng Fu | Peking University，Boya Postdoctoral Researcher
Xinyi Liu | Peking University，PhD Student
15:40-16:00 - Intel's PyTorch Journey: Open Source Optimization Makes AI More Accessible
Mingfei Ma | Intel Asia-Pacific Research & Development Ltd.，Job AI Frameworks Engineer
16:00-16:20 - FlagTree: Unified AI Compiler for Diverse AI Chips
Chunlei Men | Beijing Academy of Artificial Intelligence aka Zhiyuan Institute，R&D Manager
16:20-16:40 - KTransformers: Unleashing the Full Potential of CPU/GPU Hybrid Inference for MoE Models
Dr. Mingxing Zhang | Tsinghua University，Assistant Professor
16:40-17:00 - SGLang: An Efficient Open-Source Framework for Large-Scale LLM Serving
Liangsheng Yin | Shanghai Jiao Tong University / LMSYS，Student / Developer
