Aref Jafari

Aref Jafari is a staff researcher who works on efficient AI models

Posts by Aref Jafari

August 24, 2026

Serving 64Mi-Token Contexts on One AMD Instinct™ MI355X Node

Explore how one 8-GPU AMD MI355X node serves Kimi Linear from 1K to 64M tokens under vLLM—and the TTFT and decode throughput behind the run.

https://rocm.blogs.amd.com/artificial-intelligence/long-context-serving/README.html