Posts by Wei Cai
Deep Dive into Primus: High-Performance Training for Large Language Models
- 15 January 2026
Primus is the AMD unified training framework designed to deliver high-performance, scalable large language models (LLMs) training across multiple backends – including TorchTitan and Megatron-LM. It provides a consistent CLI interface, while each backend ships with carefully optimized configurations for popular open-source models. These backend-specific presets ensure the best out-of-the-box performance on AMD Instinct™ GPUs. In this deep dive, we walk through the best practices for achieving peak performance when training dense LLMs on Primus.
Kimi-K2-Instruct: Enhanced Out-of-the-Box Performance on AMD Instinct MI355 Series GPUs
- 16 October 2025
Learn how to boost AI inference performance with the Kimi-K2-Instruct model on AMD Instinct MI355 Series GPUs. This blog highlights benchmark results against B200 GPUs, focusing on faster time to first token (TTFT), lower latency, and higher throughput. You’ll also see how MI355X Series GPUs excel in high-concurrency workloads thanks to their larger memory capacity. By the end you’ll know how to evaluate and deploy MI355X GPUs with SGLang to scale demanding applications efficiently.
Step-Video-T2V Inference with xDiT on AMD Instinct MI300X GPUs
- 15 May 2025
The Stepfun Step-Video-T2V is a 30B parameter state-of-the-art text-to-video (T2V) model capable of generating high-quality videos of up to 204 frames. As video generation advances toward Artificial General Intelligence (AGI), such models play a key role in automating and democratizing video creation. In this blog, we introduce Step-Video-T2V with xDiT running efficiently out-of-the-box on multi-GPU systems powered by AMD Instinct™ MI300X, leveraging high-bandwidth memory and ROCm ™ for fast, scalable video generation.