Yahav Biran

Running distributed AI workloads in production requires solving three problems: package compatibility, hardware abstraction, and network configuration. AWS Neuron Deep Learning Containers (DLCs) address all three by providing open-source, production-ready images for Trainium and Inferentia. This...

As PyTorch-based LLM serving matures, the challenge shifts from monolithic inference stacks to integrating diverse hardware accelerators efficiently. This session explores how modular plugin architectures enable PyTorch models to run optimally across backends—demonstrating AWS Trainium integration...

In this interactive chalk talk, we'll collaboratively explore how to optimize LLM serving using vLLM on AWS Trainium and Inferentia chips. Through whiteboarding and hands-on discussion, we'll architect efficient deployment patterns, tackle common performance bottlenecks, and design scalable serving configurations.

Join us for a immersive, hands-on workshop to learn to deploy and optimize large language models (LLMs) for scalable inference at enterprise scale. Participants will learn to orchestrate distributed LLM serving with vLLM on Amazon EKS, enabling robust, flexible, and highly available deployments.

Learn how the open-source NxD Inference library delivers high-performance PyTorch model serving on AWS Trainium and Inferentia. We’ll show how NxDI features like continuous batching, speculative decoding, and distributed parallelism can run alongside TorchInductor-compiled CUDA kernels in a single...

Running containerized game servers on Amazon EKS using Unreal Engine? Learn how you can reduce compute costs, increase application resiliency, and future-proof your architecture with AWS Graviton and x86 processors.

In this workshop, learn how to modernize game servers by porting them from bare metal/VM to containers. Gain practical skills for how to deploy game servers to Kubernetes while meeting CPU and memory requirements, integrate matchmaking, utilize container scans in CI/CD pipelines, and observe games using custom metrics.

In this chalk talk, use AWS Managed Services (AMS) to deploy a cost-effective, containerized massively multiplayer online (MMO) game. Learn how to design a production-grade architecture with Amazon EC2 Spot Instances, Amazon EKS, Network Load Balancer, and Amazon Aurora Serverless while playing video games.

We have seen PostgreSQL customers facing buffer_content locks caused by contention of data in high concurrency or large datasets(96vCPUs, 768GiB with 30TB). We provide a benchmark and share tips with a real-world workload that leads to buffer_lock contentions. We then propose the patterns to...

Machine learning (ML) can make your business more efficient across a variety of use cases, such as product recommendations, sentiment analyses, or fraud detection. Amazon Aurora ML is a capability of Aurora that enables you to add ML-based predictions to applications via the familiar SQL programming language, so you don’t need to learn separate tools or have prior ML experience.

Amazon RDS makes it fast and simple for you to get started with familiar database engines. As your business grows, you need a cloud solution that scales with you.