Developers Blogs

Developers Blogs#

Scaling AI Inference Performance with vLLM on AMD Instinct MI355X GPUs

Explore how MI355X performs against B200 in vLLM benchmarks across DeepSeek-R1, GPT-OSS-120B, Qwen3-235B and Llama-3.3-70B.

December 08, 2025 by Jouni Hartikainen, Aarne Talman, Reima Karhila, Teemu Virolainen, Mikko Tukiainen, Bishwo Adhikari, Xavier Aguilar Fruto, Chun Fang, Stig-Arne Gronroos, Markus Hartikainen, Mustafa Khalid Masood, Olga Miroshnichenko, Tres Popp, Tuukka Sarvi, Olha Shkaravska, Jin Tao, Matti Varjokallio, Nico Holmberg, Jaakko Vainio, Faisal Azhar

The vLLM MoE Playbook: A Practical Guide to TP, DP, PP and Expert Parallelism

Learn how to combine TP, DP, PP, and EP for MoE models. Discover proven strategies to maximize performance on your vLLM deployments.

November 24, 2025 by Pin Siang Tan, Hongxia Yang, Peng Sun, Andy Luo, Jun Kang Chow, Ye Hur Cheong, Tun Jian Tan

Day 0 Developer Guide: hipBLASLt Offline GEMM Tuning Script

Learn how to improve model performance with hipBLASLt offline tuning in our easy-to-use Day 0 tool for developers to optimize GEMM efficiency

November 05, 2025 by Han Lin, Spandan Tiwari, Xinjun Niu, Chao Li, Wei Luo, Junyan Yang, Carson Liao, Chunhung Wang, Ashish Sirasao

Continuing the Momentum: Refining ROCm For The Next Wave Of AI and HPC

ROCm 7.1 builds on 7.0’s AI and HPC advances with faster performance, stronger reliability, and streamlined tools for developers and system builders.

November 05, 2025 by Anshul Gupta, Liam Berry, Saad Rahim

Ecosystems & Partners

ROCm 7.0: An AI-Ready Powerhouse for Performance, Efficiency, and Productivity

Discover how ROCm 7.0 integrates AI across every layer, combining hardware enablement, frameworks, model support, and a suite of optimized tools

September 16, 2025 by Liam Berry, Mohammed Faraaz Mustafa, Danny Guan, Saad Rahim, Aditya Bhattacharji, Marilyn Basanta

Day 0 Developer Guide: Running the Latest Open Models from OpenAI on AMD AI Hardware

Day 0 support across our AI hardware ecosystem from our flagship AMD InstinctTM MI355X and MI300X GPUs, AMD Radeon™ AI PRO R700 GPUs and AMD Ryzen™ AI Processors

August 05, 2025 by Andy Luo, Shekhar Pandey, Hongxia Yang, Mahdi Ghodsi, Charles Yang, Niles Burbank, George Wang, Kailash Gogineni, Xun Wang, Zhenyu Gu, Yao Fu, Yanyuan Qin, Anshul Gupta

Unlocking GPU-Accelerated Containers with the AMD Container Toolkit

Simplify GPU acceleration in containers with the AMD Container Toolkit—streamlined setup, runtime hooks, and full ROCm integration.

July 03, 2025 by Abhishek Patil

ROCm Revisited: Getting Started with HIP

New to HIP? This blog will introduce you to the HIP runtime API, its key concepts and installation and practical code examples to showcase its functionality.

June 06, 2025 by Liam Berry, Mohammed Faraaz Mustafa, Saad Rahim

Applications & Models

Nitro-E: A 304M Diffusion Transformer Model for High Quality Image Generation

Nitro-E is an extremely lightweight diffusion transformer model for high-quality image generation with only 304M paramters.

October 24, 2025 by Tong Shen, Jingai Yu, Dong Zhou, Dong Li, Emad Barsoum

STX-B0T: Real-time AI Robot Assistant Powered by RyzenAI and ROCm

STX-B0T explores the potential of RyzenAI PCs to power robotics applications on NPU+GPU. This blog demonstrates how our hardware and software interoperate to unlock real-time perception.

October 23, 2025 by Justin Chu, Yosi Hatekar, Vivian Cheng, Hyunji Kim, Alex Bogdan

Empowering Developers to Build a Robust PyTorch Ecosystem on AMD ROCm™ with Better Insights and Monitoring

Production ROCm support for N-1 to N+1 PyTorch releases is in progress. The AI Software Head-Up Dashboard shows status of PyTorch on ROCm.

October 21, 2025 by Hongxia Yang, Peng Sun, Nick Romero, Jeff Daily, Jithun Nair, Pruthvi Madugundu, Jagadish Krishnamoorthy, Srinivasan Subramanian, Eli Uriegas