Search All Blogs
News and Announcements
-
Designed to Create. Built to Inspire. AMD Introduces New “Zen 5” based Ryzen™ Threadripper™ 9000 Series Processors for High-End Desktops
Following our initial announcement from a few weeks ago at Computex, the new AMD Ryzen™ Threadripper™ 9000 Series processors for high-end desktops wil…
July 25, 2025
-
ISVs are the Glue that Makes Workstations Work
Workstations are more than just a collection of parts. They represent an ecosystem – one that rests on independent software vendor (ISV) certification…
July 21, 2025
-
Customers Praise 5 Years of AMD Ryzen™ Threadripper™ PRO CPUs
The launch of AMD Ryzen™ Threadripper™ PRO marked a sea change for workstation customers – and their projects.
July 18, 2025
-
Driving AMD EPYC CPU-Based Storage Solutions for Enterprise
Learn about storage solutions that AMD collaborates alongside original equipment manufacturers (OEMs) and independent software vendors (ISVs) to devel…
July 17, 2025
-
AMD Radeon™ AI PRO R9700 available in SI Partner Workstations
Available July 23, 2025 in SI-built systems, AMD Radeon™ AI PRO R9700 brings 32GB memory and RDNA™ 4 architecture power to local AI workloads.
July 17, 2025
-
AI Adoption is a Multiyear Journey. And No Enterprise can do it Alone.
Building enterprise readiness to capitalize on the enormous potential of AI is a challenge of almost unprecedented complexity and scale. The inherentl…
July 16, 2025
Technical Articles and Blogs
-
Avoiding LDS Bank Conflicts on AMD GPUs Using CK-Tile Framework — ROCm Blogs
This blog shows how CK-Tile’s XOR-based swizzle optimizes shared memory access in GEMM kernels on AMD GPUs by eliminating LDS bank conflicts
July 24, 2025
-
Benchmarking Reasoning Models: From Tokens to Answers — ROCm Blogs
Learn how to benchmark reasoning tasks. Use Qwen3 and vLLM to test true reasoning performance, not just how fast words are generated.
July 23, 2025
-
Speculative LLM Inference on the 5th Gen AMD EPYC Processors with PARD and PACE
In this blog, we will explore how PARD and AMD PACE work together to optimize inference performance for Transformer models, particularly in data cente…
July 23, 2025
-
Rethinking Local AI Lemonade Servers Python Advantage
This blog challenges the idea that Python isn’t suitable for production—by exploring how we used it to build Lemonade Server, a production-grade, high…
July 21, 2025
-
Introducing The World’s First BF16 NPU Model for SD 3.0 Medium – Try Now in Amuse 3.1
Introducing the world's first SD 3 Medium BF16 model optimized for the AMD XDNA™ 2 NPU. Try now in Amuse 3.1
July 21, 2025
-
Chain-of-Thought Guided Visual Reasoning Using Llama 3.2 on a Single AMD Instinct MI300X GPU — ROCm Blogs
Fine-tune Llama 3.2 Vision models on AMD MI300X GPU using Torchtune, achieving 2.3× better accuracy with 11B vs 90B model on chart-based tasks.
July 20, 2025
-
Announcing hipCIM: A Cutting-Edge Solution for Accelerated Multidimensional Image Processing — ROCm Blogs
Fully utilize the power of AMDs Instinct GPUs to process and interpret detailed multidimensional images with lightning speed.
July 17, 2025
-
Introducing ROCm-LS: Accelerating Life Science Workloads with AMD Instinct™ GPUs — ROCm Blogs
Accelerate life science and medical workloads with ROCm-LS, AMDs GPU-optimized toolkit for faster multidimensional image processing and vision.
July 17, 2025
---amd-platform-aware-compute-engine-(amd-pace)/3610250_Speculative_LLM_Inference_Blog_Image_1200x627.png)
