Explore the journey of serving complex real-world Machine Learning workflows at LinkedIn in this 32-minute talk. Discover how Ray serving is leveraged currently and in future plans. Learn about solutions being developed to address the growing complexity of AI-based applications and enhance AI engineer productivity. Gain insights into the needs of AI developers at LinkedIn that extend beyond simple model serving. Access the accompanying slide deck for visual references and additional details.
Overview
Syllabus
Inference Graphs at LinkedIn Using Ray-Serve
Taught by
Anyscale
Related Courses
-
High-Performance AI Model Serving with Ray Serve - A Rubrik Case Study
-
Faster Model Serving with Ray and Anyscale - Ray Summit 2024
-
Scaling Inference Deployments with NVIDIA Triton Inference Server and Ray Serve
-
Klaviyo's Journey to Robust Model Serving with Ray Serve
-
Enabling End-to-End LLMOps on Michelangelo with Ray
-
Accelerate Your GenAI Model Inference with Ray and Kubernetes
