Generative AI on AWS Courses

AI Agent Inference Performance Optimizations - vLLM vs SGLang vs TensorRT

Explore LLM inference engine optimizations comparing vLLM, SGLang, and TensorRT for high-performance AI agent deployments with expert insights from Modal and AWS practitioners.

• YouTube
• 1 hour 23 minutes
• On-Demand
• Free Video

PyTorch Data Loader Tuning and GPU Cross-Architecture Optimizations: CUDA and AMD

Explore PyTorch data pipeline optimization techniques and cross-architecture kernel development for NVIDIA CUDA and AMD ROCm GPUs, with practical insights on solving bottlenecks and writing efficient cross-hardware code.

• YouTube
• 1 hour 33 minutes
• On-Demand
• Free Video

Pre-training Mixtral MoE Model with SageMaker HyperPod - Fine-Tuning and Continued Pre-Training

Master advanced techniques for pre-training and fine-tuning Mixtral MoE models using AWS SageMaker HyperPod and SLURM, covering implementation strategies and continued pre-training approaches.

• YouTube
• 1 hour 9 minutes
• On-Demand
• Free Video

Generative AI and Large Language Models: Fine-tuning with SageMaker, PEFT, RLHF and PPO

Master advanced LLM fine-tuning techniques using Amazon SageMaker, exploring PEFT, RLHF, and PPO methodologies for optimized AI model performance and customization.

• YouTube
• 2 hours 32 minutes
• On-Demand
• Free Video

Generative AI and Large Language Models: From GPT-3 to ChatGPT with RLHF

Explore the latest advancements in generative AI, from CodeWhisperer to ChatGPT, while learning about prompt engineering and reinforcement learning techniques for improved human-AI interaction.

• YouTube
• 30 minutes
• On-Demand
• Free Video

Speed of Light Inference with NVIDIA and AMD GPUs Using the Modular Platform

Discover how to achieve lightning-fast AI inference across NVIDIA and AMD GPUs using Modular's platform, covering MAX framework, Mojo language, and cost optimization strategies.

• YouTube
• 1 hour 39 minutes
• On-Demand
• Free Video

Advanced and Accelerated Data Curation and Visualizations for LLMs with NVIDIA CuML, DBSCAN, and tSNE

Master high-performance data curation and visualization for LLMs using NVIDIA CuML, DBSCAN, and tSNE algorithms with GPU acceleration techniques.

• YouTube
• 1 hour 6 minutes
• On-Demand
• Free Video

NeurIPS 2025 AI Systems Recap

Discover key AI performance insights and hot topics from Neurips 2025 with expert analysis on cutting-edge systems optimization and engineering breakthroughs.

• YouTube
• 55 minutes
• On-Demand
• Free Video

Automated Browser Use with Amazon AGI

Discover how to automate browser interactions using Amazon's AGI technology in this focused 15-minute session with expert insights and practical implementation strategies.

• YouTube
• 15 minutes
• On-Demand
• Free Video

Diving Deep into NVIDIA Nsight Systems GPU Profiling Tools for PyTorch LLM and Computer Vision Workloads

Dive into NVIDIA Nsight Systems GPU profiling tools to optimize PyTorch LLM and computer vision workloads, focusing on data transfer optimization and performance engineering techniques.

• YouTube
• 1 hour 1 minute
• On-Demand
• Free Video

NVIDIA Dynamo Disaggregated Prefill-Decode LLM Serving and High Performance PyTorch/CUDA Optimizations

Explore NVIDIA Dynamo's disaggregated LLM serving architecture and Luminal's PyTorch/CUDA kernel optimization techniques for enhanced AI performance engineering.

• YouTube
• 1 hour 5 minutes
• On-Demand
• Free Video