Evaluating CXL Memory Pooling for Scalable LLM Inference.

Sai Krishna Vemuri, Venkata Ravi Shankar Jonnalagadda, Ajay Joshi, Rohit Sindhu, Vijay Kumar Motagi, Amandeep Singh, Praveen Kumar Rukmangada, Sachin Shaw, Vishal Tanna

Browse the full HiPC paper archive.