KubeCon + CloudNativeCon North America 2024: Full Schedule

In-person
November 12-15
Learn More and Register to Attend

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for KubeCon + CloudNativeCon North America 2024 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

Please note: This schedule is automatically displayed in Mountain Standard Time (UTC -7). To see the schedule in your preferred timezone, please select from the drop-down menu to the right, above "Filter by Date." The schedule is subject to change and session seating is available on a first-come, first-served basis.

arrow_back View All Dates

11:00am MST

Better Together! GPU, TPU and NIC Topological Alignment with DRA - John Belamaric, Google & Patrick Ohly, Intel

Friday November 15, 2024 11:00am - 11:35am MST

Salt Palace | Level 2 | 250 AD

AI/ML workloads on Kubernetes demand ultra-high performance. If your training or multi-GPU inference job spans nodes, your GPUs will use the network, talking through a NIC over local PCIe. But not all NICs are equal! To get the best performance, you need a NIC which is as "close" to the GPU as possible. Unfortunately, the Kubernetes extended resources API does not have enough information and does not give you control over which specific devices are assigned. Dynamic Resource Allocation, the successor API, gives you this power. Come to this session to learn about DRA, how it is improving overall device support in K8s, and how to use it to allocate multiple GPUs, NICs, and TPUs to get the maximum performance out of your infrastructure.

Speakers

Patrick Ohly

Principal Engineer, Intel

Patrick Ohly is a software engineer at Intel GmbH, Germany. In the past he has worked on performance analysis software for HPC clusters ("Intel Trace Analyzer and Collector") and cluster technology in general (PTP and hardware time stamping). Since January 2009 he has worked for Intel... Read More →

John Belamaric

Senior Staff Software Engineer, Google

John is a Sr Staff SWE, co-chair of K8s SIG Architecture and of K8s WG Device Management, helping lead efforts to improve how GPUs, TPUs, NICs and other devices are selected, shared, and configured in Kubernetes. He is also co-founder of Nephio, an LF project for K8s-based automation... Read More →

[PUBLIC] 2024 KubeCon NA Better Together! GPU, TPU and NIC Topological Alignment with DRA pdf

Friday November 15, 2024 11:00am - 11:35am MST
Salt Palace | Level 2 | 250 AD

AI + ML

Content Experience Level Intermediate

11:55am MST

Building Massive-Scale Generative AI Services with Kubernetes and Open Source - John McBride, OpenSauced

Friday November 15, 2024 11:55am - 12:30pm MST

Salt Palace | Level 2 | 250 AD

At OpenSauced, we power over 40,000 generative AI inferences every day, all through our in-house platform ontop of Kubernetes. The cost of doing this kind of at-scale AI inference with a third party provider API would be astronomic. Thankfully, using Kubernetes, the public cloud, and open-source technologies, we've been able to scale with relatively low costs and a lean stack. In this talk, John will walk through the journey of building a production grade generative AI system using open source technologies, open large language models, and Kubernetes. We'll also explore why we chose to build ontop of Kubernetes for our AI workloads over using a third party provider, and how we're running and managing our AI/ML clusters today. Additionally, we'll dive into the techniques we used to groom our Retrieval-Augmented-Generation pipelines for efficiency ontop of Kubernetes and other practical tips for deploying your own AI services at-scale.

Speakers

John McBride

Sr. Software Engineer, OpenSauced

John is a Sr. Software Engineer at OpenSauced where he also serves as Head of Infrastructure and AI engineer. He is the maintainer of spf13/cobra, the Go CLI bootstrapping library used throughout the CNCF landscape. In the past, he has worked on open source Kuberenetes platforms... Read More →

Kubecon 24 Building Massive Scale Generative AI Services with Kubernetes and Open Source John McBride, OpenSauced pdf

Friday November 15, 2024 11:55am - 12:30pm MST
Salt Palace | Level 2 | 250 AD

AI + ML

Content Experience Level Any

2:00pm MST

Bloomberg’s Journey to Improve Resource Utilization in a Multi-Cluster Platform - Yao Weng & Leon Zhou, Bloomberg

Friday November 15, 2024 2:00pm - 2:35pm MST

Salt Palace | Level 2 | 250 AD

Bloomberg provides an on-premises Data Science Platform (DSP) using cloud-native software to support internal AI model training. It runs on Kubernetes clusters spanning multiple data centers and featuring a diverse range of GPU types. However, managing such a large-scale and heterogeneous GPU environment poses many challenges, such as improving resource utilization, reducing operational costs, and scheduling workloads across different GPU types. In collaboration with the Karmada community, Bloomberg's DSP team has aimed to tackle these challenges by addressing multi-cluster batch job management problems. This talk will delve into the approaches the team has adopted, including: - Intelligently scheduling GPU workloads across multiple clusters - Using Karmada's resource interpreter to support Kubernetes Custom Resource Definitions (CRDs) on top of a multi-cluster architecture - Building a highly available Karmada control plane - Establishing a consistent training job submission interface

Speakers

Leon Zhou

Software Engineer, Bloomberg

Leon Zhou is a software engineer on the Data Science Platform engineering team at Bloomberg. With prior NLP experience, he is now building ML platforms to facilitate machine learning development. He is interested in ML infrastructure to enable large-scale training and complex pipelines... Read More →

Yao Weng

Senior Software Engineer, Bloomberg

Yao Weng is a Senior Software Engineer on Bloomberg’s Data Science Platform engineering team. She has contributed extensively to optimizing the company’s Kubernetes environment for high performance compute, model inference, and workflow orchestration. Yao Weng obtained her Ph.D... Read More →

Kubecon NA 2024 Slides Bloomberg's Journey to Improve Resource Utilization in a Multi Cluster Platform pptx

Friday November 15, 2024 2:00pm - 2:35pm MST
Salt Palace | Level 2 | 250 AD

AI + ML

Content Experience Level Intermediate

2:55pm MST

Cloud-Native AI: Wasm in Portable, Secure AI/ML Workloads - Miley Fu, Second State

Friday November 15, 2024 2:55pm - 3:30pm MST

Salt Palace | Level 2 | 250 AD

In this talk, we present Wasm as a pioneering solution for running AI/ML workloads in cloud-native environments. Our focus is on demonstrating how Wasm (on the server) facilitates the execution of AI models, such as Llama3, Grok by X, Mixtral etc, across diverse cloud and edge platforms without sacrificing performance. We will discuss the advantages of using Rust and WebAssembly in AI/ML workloads, highlighting aspects like portability, speed, and security. Real-world examples will illustrate the deployment of AI inference models using Wasm runtime in Kubernetes environments, showcasing seamless orchestration and execution across varied devices. This session is aimed at cloud-native practitioners and AI/ML enthusiasts eager to explore innovative approaches in AI deployment.

Speakers

Miley Fu

DevRel, WasmEdge

Miley is a Developer Advocate with a passion for empowering developers to build and contribute to open source. With over 5 years of experience working on WasmEdge runtime in CNCF sandbox as the founding member, she talked at KubeCon, KCD Shenzhen, CloudDay Italy, DevRelCon, Open Source... Read More →

Friday November 15, 2024 2:55pm - 3:30pm MST
Salt Palace | Level 2 | 250 AD

AI + ML

Content Experience Level Beginner

4:00pm MST

Best Practices for Deploying LLM Inference, RAG and Fine Tuning Pipelines on K8s - Meenakshi Kaushik & Shiva Krishna Merla, NVIDIA

Friday November 15, 2024 4:00pm - 4:35pm MST

Salt Palace | Level 2 | 250 AD

In this session, we'll cover best practices for deploying, scaling, and managing LLM inference pipelines on Kubernetes (K8s). We'll explore common patterns like inference, retrieval-augmented generation (RAG), and fine-tuning. Key challenges addressed include: [1]. Minimizing initial inference latency with model caching [2] Optimizing GPU usage with efficient scheduling, multi-GPU/node handling, and auto-quantization [3] Enhancing security and management with RBAC, monitoring, auto-scaling, and support for air-gapped clusters We'll also demonstrate building customizable pipelines for inference, RAG, and fine-tuning, and managing them post-deployment. Solutions include [1] a lightweight standalone tool built using operator pattern and [2] KServe, a robust open-source AI inference platform. This session will equip you to effectively manage LLM inference pipelines on K8s, improving performance, efficiency, and security

Speakers

Meenakshi Kaushik

Product Management, Nvidia

Meenakshi Kaushik leads product management for NIM Operator and KServe.. Meenakshi is interested in the AI and ML space and is excited to see how the technology can enhance human well-being and productivity.

Shiva Krishna Merla

Senior Software Engineer, NVIDIA

Shiva Krishna Merla is a senior software engineer on the NVIDIA Cloud Native team where he works on GPU cloud infrastructure, orchestration and monitoring. He is focused on enabling GPU-accelerated DL and AI workloads in container orchestration systems such as Kubernetes and OpenShift... Read More →

best practices llm inference rag finetuning pdf

Friday November 15, 2024 4:00pm - 4:35pm MST
Salt Palace | Level 2 | 250 AD

AI + ML

Content Experience Level Beginner

4:55pm MST

Best of Both Worlds: Integrating Slurm with Kubernetes in a Kubernetes Native Way - Eduardo Arango Gutierrez, NVIDIA & Angel Beltre, Sandia National Laboratories

Friday November 15, 2024 4:55pm - 5:30pm MST

Salt Palace | Level 2 | 250 AD

It's not always clear which container orchestration system is best suited for a given use case. Slurm, for example, is often preferred over Kubernetes when running large-scale distributed workloads. As a result, organizations areoften faced a hard choice: do they deploy Slurm or Kubernetes to service the rising demands of their AI/ML workloads. In this talk, we introduce K-Foundry, an open-source custom controller for KCP that translates Kubernetes jobs to Slurm jobs and exposes Slurm nodes and cluster info as Kubernetes Custom Resource Definitions (CRDs). This integration combines Slurm’s robust job scheduling with Kubernetes' dynamic orchestration and API-driven ecosystem, easing the administration of both clusters through a common API. This session will end with a live demo, where attendees will see how this integration bridges the gap between cloud and HPC, facilitating resource management and optimizing performance for large-scale AI and LLM tasks.

Speakers

Eduardo Arango Gutierez DE

Senior systems software engineer, NVIDIA

Eduardo is a Senior Systems Software Engineer at NVIDIA, working on the Cloud Native Technologies team. Eduardo has focused on enabling users to build and deploy containers on distributed environments.

Angel Beltre

Senior Member of Technical Staff, Sandia National Laboratories

Angel Beltre serves as a senior member of the technical staff within the Scalable System Software department at Sandia National Laboratories. He is a contributor to the CSSE Computing-as-a-Service (CaaS) initiative, aimed at streamlining the deployment of modeling and simulation tools... Read More →

Friday November 15, 2024 4:55pm - 5:30pm MST
Salt Palace | Level 2 | 250 AD

AI + ML

Content Experience Level Intermediate