Explore the development and future of multi-GPU inference in vLLM through this Ray Summit 2024 conference talk delivered by Sangbin Cho from Anyscale and Murali Andoorveedu from Centml. Gain deep insights into the distinct challenges of distributed inference for large language models compared to distributed training. Learn about key parallelism strategies including tensor, pipeline, and expert parallelism, with detailed explanations of their mechanisms. Through a practical vLLM case study, discover how to build optimized architectures for efficient distributed inference across multiple GPUs. Understand the current state and future trajectory of scaling LLM inference, gaining valuable knowledge about this crucial aspect of AI infrastructure development.
Overview
Syllabus
The Evolution of Multi-GPU Inference in vLLM | Ray Summit 2024
Taught by
Anyscale
Related Courses
-
Databricks' vLLM Optimization for Cost-Effective LLM Inference - Ray Summit 2024
-
The State of vLLM - Advancements in LLM Inference and Serving
-
Handshake's Approach to Content Tagging with vLLM and Anyscale
-
Optimizing LLM Inference with AWS Trainium, Ray, vLLM, and Anyscale
-
Efficient Large-Scale Language Model Training on GPU Clusters
-
Faster Model Serving with Ray and Anyscale - Ray Summit 2024
