| 1 |
From Open Source Adoption to Open Source Innovation: China’s Next Chapter - Professor Lu Shouqun |
keynote |
|
|
1:51 |
| 2 |
Open Source for the AI Era - Jonathan Bryce & Horace Li, The Linux Foundation |
concept |
|
AI & ML |
10:59 |
| 3 |
Beyond Multimodal: Building Full‑Modal AGI Via Open‑Weight - Ryan Lee, MiniMax |
concept |
|
|
3:42 |
| 4 |
Operating Frontier Intelligence at Scale - Chris Aniszczyk & Xiao Zhang |
case study |
|
|
20:00 |
| 5 |
Tidal Auto-scaling for Training and Inference Based on Kubernetes + KEDA - Jun Zheng & Tan Pei Xiang |
concept |
|
Autoscaling & performance, AI & ML |
7:27 |
| 6 |
Building Frontier Intelligence in the Open - Mark Collier, PyTorch Foundation |
concept |
|
|
11:05 |
| 7 |
Ascend & PyTorch: Pioneer New AI Open Ecosystem - Liang Zhang, Huawei |
concept |
|
AI & ML |
5:18 |
| 8 |
Towards Device-agnostic PyTorch: Building Unified Infrastructure for a Multi-Backend... Wei Li |
concept |
|
|
4:56 |
| 9 |
Inside VLLM: Production Best Practices, Model Integration and Road Map - Kaichao You, Inferact |
concept |
|
|
1:42 |
| 10 |
PD Disaggregation VLLM Deployment on Alternative AI Accelerators Using Llm-d - 纪飞 王 & Mengxuan Li |
concept |
|
AI & ML |
8:32 |
| 11 |
From Containers To Agents: The Next Cloud Native - Di Xu, Xiaohongshu |
case study |
Xiaohongshu |
|
5:39 |
| 12 |
What AI Agents Need From Open Infrastructure - Yaya Xia, Ant Group |
concept |
|
AI & ML |
4:45 |
| 13 |
Building an Agent Runtime With Open Infrastructure - Yaya Xia & Xu Wang, Ant Group |
concept |
|
|
9:01 |
| 14 |
What Powers Frontier Intelligence - Thierry Carrez, OpenInfra Foundation |
keynote |
|
AI & ML |
10:19 |
| 15 |
Road from Kata Containers to Confidential Containers + GPUs: From First Commit to... Zvonko Kaiser |
concept |
|
AI & ML, Serverless & runtimes |
5:23 |
| 16 |
HyperParallel: A SuperPoD-Aware Distributed Acceleration Library - Teng Su & Shendi Wang, Huawei |
concept |
|
|
9:03 |
| 17 |
Build a Unified Heterogeneous AI Computing Ecosystem for PyTorch - Zesheng Zong, Huawei |
concept |
|
AI & ML |
4:04 |
| 18 |
Serving Qwen at Scale: Multi-Cluster AI Infrastructure on Karmada - Jionghang Cai, Alibaba |
case study |
Alibaba |
AI & ML |
3:33 |
| 19 |
Meet the Community Behind the Open Source AI Stack - Panel |
concept |
|
AI & ML |
9:56 |
| 20 |
Building Frontier AI Infra: SGLang and Miles - Ke Bao, RadixArk |
concept |
|
AI & ML |
5:32 |
| 21 |
A Cloud Native Stack From Bare Metal To Tokens for Large-Scale AI Inference - Trong Vinh Nguyen |
concept |
|
AI & ML |
4:20 |
| 22 |
All-or-Nothing No More: Taming Kubernetes Impersonation With Granular Controls - Jian Qiu |
concept |
|
Security |
24:22 |
| 23 |
From Disk Images to Container Images: Deploying bootc to Bare Metal with Kubernetes... Steve Baker |
concept |
|
|
22:43 |
| 24 |
vLLM-Helion: SOTA LLM Performance by advanced autotuning and fine-grained dispatching - Sean Chen |
concept |
|
Autoscaling & performance, AI & ML |
25:34 |
| 25 |
Why Your TTFT Lies: Diagnosing PD-Disaggregated LLM Inference with Minimal... Nicole Li & Kebe Liu |
concept |
|
AI & ML |
31:13 |
| 26 |
Escaping the Vendor Trap: A Journey for Migrating Legacy... Trong Vinh Nguyen & Quoc Dat Le |
case study |
|
|
32:51 |
| 27 |
Non-Invasive AI Agent Observability With OBI - Haibin Zhang, Alibaba Cloud & Endre Sara, Causely |
concept |
|
Observability, AI & ML |
28:48 |
| 28 |
Write Once, Run Anywhere: PyTorch’s Generalization Journey - Yu Guangye & Eikan Wang, Intel |
case study |
Intel |
|
30:49 |
| 29 |
To Cache or Not to Cache? A Tiered KVCache Storage System for... Jingbin Zhang, Wang Cong & yun bai |
concept |
|
Storage & data |
25:08 |
| 30 |
The State of the PyTorch Ecosystem in 2026: Global Trends and China’s Rising Role - Wei Wang |
concept |
|
|
18:14 |
| 31 |
What We Learned Securing AI Agents at Scale on Multi-Tenant Kubernetes Clusters - Pengfei Ni |
case study |
|
Platform engineering, AI & ML |
25:20 |
| 32 |
One Size Fits None: Lightweight Workload-Specialized Confidential Containers - Kailun Qin |
concept |
|
|
25:21 |
| 33 |
End-to-End Observability for LLM Inference: From Token To GPU - Jared Tan, Murphy Chen & Nicole Li |
case study |
Murphy Chen |
Observability, AI & ML |
31:54 |
| 34 |
Turning Fragmented GPU Clusters Into One Elastic Compute Pool - ChongKang Tan, Ant Group |
concept |
|
AI & ML |
32:48 |
| 35 |
Training Through Failures: How Meta Keeps 100k-GPU Jobs Alive with... Tristan Rice & Amir Afzali |
concept |
|
AI & ML |
24:35 |
| 36 |
Kubernetes DRA Architecture: Scheduling, Status, and Topology at Scale - Paco Xu & Kang Zhang |
case study |
|
Autoscaling & performance |
34:14 |
| 37 |
veRL: Extreme Optimization Practices for Ultra-Large-Scale MoE Models - Carson Wu |
concept |
|
|
31:06 |
| 38 |
In-Place PVC Re-Binding: Zero-Downtime Disk Migration Using Only... Maxim Nazarenko & Nibir Bora |
case study |
|
|
21:30 |
| 39 |
Secure AI Agent Sandboxing With OpenStack Zun and Kata Container - Wenjie Bao, ZTE |
concept |
|
AI & ML |
27:37 |
| 40 |
Redesigning OpenStack I18n for the AI Era: Weblate & Zero-GPU AI - Seongsoo Cho & DaGyeong Kim |
concept |
|
AI & ML |
30:03 |
| 41 |
From Cloud to AI: How Kata Containers 4.0 Reinvents the Sandbox for the... Fupan Li & Xuewei Niu |
case study |
|
AI & ML, Serverless & runtimes |
25:24 |
| 42 |
Pathless First: Redefining Runc Container Security Against ProcFS-Based Attacks - Fubang Li |
concept |
|
Security |
29:44 |
| 43 |
VLLM KV Cache Management: From Cache Reuse To Agent Scenario Optimization - Mengqing Cao & 玺源 王 |
case study |
|
|
33:40 |
| 44 |
Minutes, Not Weeks: Long-Term Memory for AI Applications With PowerMem - Yihang Li |
concept |
|
AI & ML |
27:47 |
| 45 |
Gravity of Ecosystems: Pollinating the Modern AI Orchestrator - Wenjia Zhang & Bo Fu, Google |
concept |
|
AI & ML |
35:33 |
| 46 |
Building a Multi-Cluster Progressive Delivery Platform with Karmada & Argo - Zhuang Zhang |
concept |
|
CI/CD & GitOps |
6:00 |
| 47 |
Eliminating Adaptation Latency: Day-0 Inference for New Models on... Xiaoshuang Wang |
concept |
|
AI & ML |
5:39 |
| 48 |
Zero-Trust Traffic Governance for Kubernetes AI Agent Sandboxes - Bingshen Wang & Bo Kang Li |
concept |
|
AI & ML |
30:05 |
| 49 |
Fast Restarts, Not Just Fast Starts: Accelerating Pod Recovery - Baofa Fan, DaoCloud |
concept |
|
|
7:47 |
| 50 |
Scaling Digital Employees at China Merchants Bank in Production: A Controlled AI... Jiahang Xu |
case study |
China |
Autoscaling & performance, AI & ML |
42:19 |
| 51 |
Building Portable Large Models on Heterogeneous AI... Mengsi Lyu, Hongjun Zhang & Yufeng Lyu |
concept |
|
AI & ML |
1:06:31 |
| 52 |
Advanced NCCL Tutorial: Beyond Collectives - Jeff Hammond & Hanyue He & Ke Wen, NVIDIA |
tutorial |
|
|
1:17:18 |
| 53 |
Empower Open Edge Computing on RISC-V - Tiejun Chen, RISC-V International |
concept |
|
Edge & IoT |
5:23 |
| 54 |
Can Stateful AI Agents Scale To Zero? - Peng Li, Alibaba Cloud |
concept |
|
Storage & data, AI & ML |
4:54 |
| 55 |
Cybertwin-based Cloud Native Network (CCNN): Network Architecture... Dandan Liang & Weizhou Lan |
concept |
|
|
25:15 |
| 56 |
Dragonfly's CNCF Graduation Journey and Large-Scale AI Model Distribution... Fengjun Lyu & Wenbo Qi |
case study |
|
AI & ML |
24:43 |
| 57 |
Architecting Secure Agentic Workflows on Kubernetes: A... Vincent Caldeira & Morgan Foster |
concept |
|
|
39:55 |
| 58 |
Building AI4S Systems for Scientific Research on Kubernetes - Jiamu Liu & Yanjun Chen |
concept |
|
|
37:15 |
| 59 |
Agile Readiness: Leveraging CI Relay and Full-Scale Test Reuse - Jiawei Li & Jingwei Huang, Huawei |
concept |
|
|
29:56 |
| 60 |
Edge Resource Control in KubeEdge:Safely Holding and Releasing Pod Updates for... Feng Gao |
concept |
|
Edge & IoT |
3:34 |
| 61 |
KV Cache: Accelerating AI Inference on Intel CPU - Bin Yang, Intel |
concept |
|
AI & ML |
14:37 |
| 62 |
Before vLLM starts: Preflight Checks for LWS for LLM Inference on K8S - Peter Pan, DaoCloud |
concept |
|
AI & ML |
7:21 |
| 63 |
Accelerating RL With AgentCube: Cloud Native Multi-Agent Collaboration - Zhencheng Lee |
concept |
|
|
18:58 |
| 64 |
Speedy but Sturdy PyTorch Optimizers - Jane Xu, Meta Platforms Inc |
concept |
|
|
5:31 |
| 65 |
Spec-Driven Evolution: How AI Agents are Rewriting the... Bertrand Souville & Muhammad Hamza |
concept |
|
AI & ML |
29:49 |
| 66 |
Hibernate and Evolving: Taming OpenClaw With OpenKruise Agents - Zhang Zhen, Alibaba Cloud |
concept |
|
|
34:03 |
| 67 |
Project Lightning Talk: Atlantis: Terraform Pull Request Automation for Cloud Native... Rui Chen |
concept |
|
|
5:49 |
| 68 |
Exploring HiFloat8: A Tapered Format Complementing the FP8 Ecosystem for Robust Model... Yun Zhao |
concept |
|
|
25:53 |
| 69 |
From Chatbots To Agentic AI: Running NVIDIA Dynamo the Kubernetes Way - Xianglong Lu & Bo Chu |
case study |
|
AI & ML |
37:54 |
| 70 |
Dragonfly V2.5.0 - Intro, Updates, Data Distribution in AI Infrastructure - Wenbo Qi & Chenyu Zhang |
concept |
|
AI & ML |
30:12 |
| 71 |
Project Lightning Talk: Let’s Talk About Headlamp, the Extensible Open-Source... Emily Chen |
concept |
|
|
4:49 |
| 72 |
Beyond Model Sharding: Atomic Scheduling and Disaggregated LLM Serving... Kay Yan & Chen Zicong |
concept |
|
Autoscaling & performance, AI & ML |
39:10 |
| 73 |
Project Lightning Talk: Run Sandbox Securely and Cost-Effectively with OpenKruise... Zhang Zhen |
concept |
|
|
5:12 |
| 74 |
Zuul and OpenClaw, Safe Agentic Coding Via Human Collaboration Tools - Monty Taylor, WanderTracks |
concept |
|
|
38:01 |
| 75 |
Evolving Argo Workflows for AI: New Features, Tuning, and Multi-Tenant... Shuangkun Tian & Yashi Su |
concept |
|
CI/CD & GitOps, Platform engineering, AI & ML |
24:45 |
| 76 |
Project Lightning Talk: Multi-cluster Orchestration System: Karmada... Hongcai Ren & Yiheng Ci |
concept |
|
|
6:56 |
| 77 |
10 Years of Cilium: Connecting, Securing, and Simplifying the... Liyi Huang, Tingjin Ye & Yashi Su |
concept |
|
Networking |
30:49 |
| 78 |
Redefining LLM Training Through Atomic Components and Serverless TaaS - Tan Pei Xiang |
concept |
|
AI & ML, Serverless & runtimes |
39:24 |
| 79 |
KernelAgent: Hardware-Guided GPU Kernel Optimization via... Kaiming Cheng, Jack Khuu & Laura Wang |
concept |
|
AI & ML |
18:18 |
| 80 |
Project Lightning Talk: Architecture Without Gatekeepers: Decoupling for Neutrality - Sergey Pronin |
concept |
|
|
5:44 |
| 81 |
Project Lightning Talk: KubeEdge Everywhere: Latest Project Update with... Hongbing Zhang |
concept |
|
Edge & IoT |
9:07 |
| 82 |
Beyond Static Pods: Dynamic GPU Sharing and Low-Latency Model Switching for LLM... 夕宁 & Jun Duan |
concept |
|
AI & ML |
34:04 |
| 83 |
Helion's New CuTe DSL and Pallas Backends and How we Built Them via Agents - Dunfan Lu & Jason Ansel |
concept |
|
|
41:05 |
| 84 |
Solving Industrial Challenges with KubeEdge: A Post-Graduation Report - Yue Bao, Huan Wei, Yin Ding |
case study |
Unknown industrial KubeEdge adopters |
Edge & IoT |
25:57 |
| 85 |
8 Million Tasks Daily: Driving Efficiency in Multi-Tenant Data... JIanxiang Sun & Shuangkun Tian |
case study |
|
Autoscaling & performance, CI/CD & GitOps, Platform engineering, Cost & efficiency |
24:57 |
| 86 |
Project Lightning Talk: From Static Slices To Elastic GPUs: Dynamic MIG With HAMI - 纪飞 王, Dynamia |
case study |
Dynamia |
|
6:41 |
| 87 |
Serving AI at Massive Scale: The Cloud Native Inference Plane Behind Huawei... Kevin Wang, Jun Ding |
case study |
Massive |
AI & ML |
39:18 |
| 88 |
How Intsig Serves Billions of Document Scans: GPU Virtualization at... Mengxuan Li & Walter Duan |
concept |
|
AI & ML |
22:01 |
| 89 |
Multi-cluster Orchestration System: Karmada Updates... - Hongcai Ren, Huawei & Zongqing Li, Trip.com |
concept |
|
|
33:48 |
| 90 |
Project Lightning Talk: Let's Talk About Perses, the Open Specification for... Leon Nunes |
concept |
|
|
4:05 |
| 91 |
Accelerating Sequential Recommender Models in the PyTorch Ecosystem - Zan Huang & Jiayu Sun, NVIDIA |
concept |
|
|
34:04 |
| 92 |
Declarative Underlays: Scaling Purpose-Built Infrastructure(Clusters)... HanSol Park & Kangsub Song |
concept |
|
Autoscaling & performance |
30:55 |
| 93 |
Volcano: A Unified Scheduling Platform for Cloud Native AI - Chen Zicong, Huawei & DongYang Wang |
concept |
|
Autoscaling & performance, AI & ML |
30:14 |
| 94 |
Behind the Scenes of Building a Gateway API Dataplane... Norwin Schnyder & Huabing (Robin) Zhao |
concept |
|
Networking |
31:21 |
| 95 |
Self-Healing Rollouts: Automating Production Fixes With Agentic AI - Kevin Dubois & Daniel Oh |
concept |
|
AI & ML |
35:09 |