Anyscale Courses

Fast, Flexible, and Scalable Data Loading for ML Training with Ray Data

Explore Ray Data's fast, flexible, and scalable data loading for ML training. Learn how it matches PyTorch and TensorFlow performance while offering advanced features for scale and diverse data types.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Build Augmented Reality Maps With Ray

Explore how Niantic leverages Ray to build precise AR maps, streamline research-to-production pipelines, process user scans efficiently, and create complex 3D environments for immersive experiences.

• YouTube
• 27 minutes
• Self-Paced
• Free Video

Embeddings and Vectors: The Key to Production AI

Explore how teams program AI with data using embeddings and vectors, and learn about future approaches for building production AI applications.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Ray, Knative, and Running Serverless Workloads in the Cloud

Explore serverless computing with Ray and Knative. Compare approaches, uncover best practices, and learn about potential pitfalls in serverless development for machine learning and HTTP services.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

Enabling Cost-Efficient LLM Serving with Ray Serve

Discover how Ray Serve optimizes LLM deployment, reducing costs through fine-grained autoscaling, continuous batching, and model parallel inference. Learn to easily deploy Hugging Face models with these optimizations.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Inference Graphs at LinkedIn Using Ray-Serve

Explore LinkedIn's journey in serving complex ML workflows using Ray-Serve, addressing AI application complexity and enhancing AI engineer productivity.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Open Source LLMs: Viable for Production or a Low-Quality Toy?

Explore Llama 2 models' strengths and weaknesses compared to ChatGPT, examining quality, cost, and usability. Learn when to consider open source LLMs and available options for AI development.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

Scaling Computer Vision Models with Ray - A Cost-Effective and Efficient Distributed Training Framework

Scale computer vision models efficiently using Ray's distributed training framework. Compare performance with Kubeflow, leveraging cost-effective S3 storage and optimized data processing for improved speed and GPU utilization.

• YouTube
• 35 minutes
• Self-Paced
• Free Video

Building Production AI Applications with Ray Serve

Explore Ray Serve's capabilities for efficient ML model deployment, including scalability, high availability, and cost optimization. Watch a live demo of serving an ML application on the Anyscale platform.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

SkyPilot - Run AI on Any Cloud

Explore SkyPilot, an open-source framework for running AI and batch jobs across clouds. Learn how it maximizes GPU availability, reduces costs, and simplifies cloud-agnostic execution for AI practitioners.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Ray Data Streaming for Large-Scale ML Training and Inference

Explore Ray Data streaming for scaling ML pipelines across CPU/GPU clusters. Learn to optimize preprocessing, training, and inference workflows in distributed environments.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Perplexity AI: Building the World's Best LLM-Powered Search Engine in 6 Months

Explore the engineering challenges and opportunities in building Perplexity.ai, an LLM-powered answer engine, with insights from founder Aravind Srinivas on rapid development and resource optimization.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Building Instacart's ML Training Platform on Ray

Explore Instacart's ML Training Platform built on Ray, featuring standard runtimes and advanced capabilities for distributed deep learning models using Ray AIR and KubeRay.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Gorilla: Large Language Models Connected with Massive APIs

Explore Gorilla LLM's advanced capabilities in API call generation, adaptation to document changes, and hallucination mitigation. Learn about this open-source project's impact on AI development.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Large Language-Style Universal Models for Short Video Recommendations

Explore a ray-based solution for large-scale video recommendations, featuring a single big model with sparse inputs/outputs and universal graph search algorithm. Learn about its advantages and empirical results.

• YouTube
• 30 minutes
• Self-Paced
• Free Video